{"release":{"schemaVersion":"maha-epistemic-release/1.0","releaseId":"epirelease_9358ae269fab40c8bfb92a15984a99cb","releaseKind":"initial","status":"active","recordId":"urn:maha:record:mechanistic-interpretability-polysemantic-neurons","domainSlug":"mechanistic-interpretability","targetSha256":"sha256:0ff0aff68c87fff92e7cc21e61a0e60da55ba57e5bc4199fc0d6f8ee11da78ad","canonicalPath":"/knowledge/mechanistic-interpretability/mechanisms/mechanistic-interpretability-polysemantic-neurons","canonicalVersion":"1.0.0","supersedesReleaseId":null,"approvals":[{"scope":"boundary-adequacy","reviewId":"epireview_19dd41a78c9f4a09885c545dd381c528","reviewSha256":"sha256:7c23efcac7ce0a6ef58b0775c5085eb94946ca943774b1dac1ee93b353e8b413","reviewedAt":"2026-08-25T09:34:36.598Z","reviewerKind":"internal-editorial","reviewMethod":"Deterministic exact-hash checks, public source-resolution evidence, source-to-claim audit, unsupported-inference audit, and AI-assisted internal editorial inspection. No external reviewer participated."},{"scope":"domain-fidelity","reviewId":"epireview_33a1f806ed944abbb24ac3e796e4dbd8","reviewSha256":"sha256:5ee377e0bed7e00a467ae995f6ddaedf2c4ac83bd9d6dce5ef50fdaf3b68da91","reviewedAt":"2026-08-25T09:34:36.529Z","reviewerKind":"internal-editorial","reviewMethod":"Deterministic exact-hash checks, public source-resolution evidence, source-to-claim audit, unsupported-inference audit, and AI-assisted internal editorial inspection. No external reviewer participated."},{"scope":"rights-and-locator","reviewId":"epireview_ac9bd5a76b7940628bb3908ad2621d0a","reviewSha256":"sha256:018df7cee84343ee200cb184d2da50fa5480f1d8434742181fafa0cd0344fff2","reviewedAt":"2026-08-25T09:34:36.666Z","reviewerKind":"internal-editorial","reviewMethod":"Deterministic exact-hash checks, public source-resolution evidence, source-to-claim audit, unsupported-inference audit, and AI-assisted internal editorial inspection. No external reviewer participated."},{"scope":"source-fidelity","reviewId":"epireview_97cf5a964d6f40dbb65268b1da410191","reviewSha256":"sha256:3e29ee70895b542a45ec260af3d17305a926fd5d07809ad8d99a048bbf8fc374","reviewedAt":"2026-08-25T09:34:36.416Z","reviewerKind":"internal-editorial","reviewMethod":"Deterministic exact-hash checks, public source-resolution evidence, source-to-claim audit, unsupported-inference audit, and AI-assisted internal editorial inspection. No external reviewer participated."}],"assuranceTier":"internally-reviewed-canonical","releaseAuthority":{"authoritySha256":"sha256:38616eafd13c4ad603a3a3a9e445f3862fb29b54385aa571c197a2923e302785","attribution":"withheld-by-consent"},"publicChangeSummary":"Initial canonical publication in the eight-domain internal-review throughput canary.","recordSha256":"sha256:a98f3991ac8186fdce269bfd35cd3d8823ea2705562f6b01f7cf8bf719654748","gateDecision":{"reasons":[],"recordId":"urn:maha:record:mechanistic-interpretability-polysemantic-neurons","publicEligible":true,"evaluatedAgainst":"maha-epistemic/1.0"},"releasedAt":"2026-08-25T09:35:31.319Z","releaseSha256":"sha256:482eb8261317445db33e36ea159cf601345c45c15ff578a2b23e27f5edc72607","withdrawal":null},"provenance":{"schemaVersion":"maha-epistemic/1.0","evidencePolicyVersion":"mps/0.1","recordId":"urn:maha:record:mechanistic-interpretability-polysemantic-neurons","canonicalPath":"/knowledge/mechanistic-interpretability/mechanisms/mechanistic-interpretability-polysemantic-neurons","contentHash":"sha256:a98f3991ac8186fdce269bfd35cd3d8823ea2705562f6b01f7cf8bf719654748","generatedAt":"2026-08-25T09:35:31.319Z","publicationDecision":{"recordId":"urn:maha:record:mechanistic-interpretability-polysemantic-neurons","publicEligible":true,"evaluatedAgainst":"maha-epistemic/1.0","reasons":[]},"claims":[{"id":"urn:maha:claim:mechanistic-interpretability-polysemantic-neurons","scope":"Limited to Definitions, toy models, geometry, sparsity, and feature-interference experiments. in “Toy Models of Superposition”; this candidate records the concept boundary and does not pool results from uncited systems or studies.","boundary":"Polysemantic neurons does not by itself establish system-level performance, safety, manufacturability, scalability, economic advantage, clinical benefit, or deployment readiness.","claimKind":"theoretical-model","sourceIds":["source-mechanistic-interpretability-superposition"],"statement":"The cited source supports treating polysemantic neurons as a distinct mechanism within the stated mechanistic interpretability scope.","replication":{"asOfDate":"2026-08-24","assessment":"Independent replication and cross-platform transfer have not been compiled for this candidate; the evidence maturity refers only to the bounded source contract.","independentReplicationCount":null},"uncertainty":{"kind":"qualitative","statement":"No cross-source quantitative interval is asserted. Definitions, operating conditions, samples, instruments, and outcome measures must be checked against the exact cited locator during review."},"evidenceMaturity":"single-study"}],"sources":[{"id":"source-mechanistic-interpretability-superposition","url":"https://transformer-circuits.pub/2022/toy_model/index.html","title":"Toy Models of Superposition","rights":{"note":"The candidate uses original boundary language and a short paraphrase linked to the cited source. No source passage, figure, or table is reproduced.","basis":"citation-with-paraphrase","quotationUsed":false},"authors":["Nelson Elhage","Tristan Hume","Catherine Olsson","et al."],"boundary":"A toy-model mechanism does not establish that every feature in a production model has the same geometry or semantics.","publisher":"Transformer Circuits Thread","establishes":"The work develops toy models in which neural networks represent more features than available dimensions under specified sparsity conditions.","identifiers":[{"value":"https://transformer-circuits.pub/2022/toy_model/index.html","scheme":"url"}],"publishedAt":"2022-09-14","exactLocator":"Definitions, toy models, geometry, sparsity, and feature-interference experiments."}],"reviewEvents":[{"reviewId":"epireview_97cf5a964d6f40dbb65268b1da410191","scope":"source-fidelity","targetSha256":"sha256:0ff0aff68c87fff92e7cc21e61a0e60da55ba57e5bc4199fc0d6f8ee11da78ad","reviewedAt":"2026-08-25T09:34:36.416Z","verdict":"approve","supersedesReviewId":null},{"reviewId":"epireview_33a1f806ed944abbb24ac3e796e4dbd8","scope":"domain-fidelity","targetSha256":"sha256:0ff0aff68c87fff92e7cc21e61a0e60da55ba57e5bc4199fc0d6f8ee11da78ad","reviewedAt":"2026-08-25T09:34:36.529Z","verdict":"approve","supersedesReviewId":null},{"reviewId":"epireview_19dd41a78c9f4a09885c545dd381c528","scope":"boundary-adequacy","targetSha256":"sha256:0ff0aff68c87fff92e7cc21e61a0e60da55ba57e5bc4199fc0d6f8ee11da78ad","reviewedAt":"2026-08-25T09:34:36.598Z","verdict":"approve","supersedesReviewId":null},{"reviewId":"epireview_ac9bd5a76b7940628bb3908ad2621d0a","scope":"rights-and-locator","targetSha256":"sha256:0ff0aff68c87fff92e7cc21e61a0e60da55ba57e5bc4199fc0d6f8ee11da78ad","reviewedAt":"2026-08-25T09:34:36.666Z","verdict":"approve","supersedesReviewId":null}]},"privacyBoundary":"Operational actor fingerprints, bearer credentials, private reviewer profiles, affiliations, conflicts, and non-consented authority identity fields are excluded."}