Governed candidate corpus · review pending
Mechanistic interpretability
Features, circuits, interventions, sparse representations, causal tests, and faithfulness criteria represented separately from explanatory confidence.
Primary stress point
A human-readable feature label, probe, attention pattern, or ablation effect does not by itself establish a complete or faithful causal explanation.
Canonical factory depth
11 of 30 governed factory records are active canonical releases. The candidate corpus remains below the public line until each record independently passes exact-hash review and release.
Canonical public layer
Records that passed the gate
Representation probing boundary
A source-bounded comparison record for representation probing boundary within mechanistic interpretability.
Inspect claims and provenance →
Induction head circuits
A source-bounded concept record for induction head circuits within mechanistic interpretability.
Inspect claims and provenance →
Neural feature superposition
A source-bounded concept record for neural feature superposition within mechanistic interpretability.
Inspect claims and provenance →
Sparse autoencoder dictionaries
A source-bounded concept record for sparse autoencoder dictionaries within mechanistic interpretability.
Inspect claims and provenance →
Attention pattern evidence
A source-bounded measurement record for attention pattern evidence within mechanistic interpretability.
Inspect claims and provenance →
Superposition geometry
A source-bounded measurement record for superposition geometry within mechanistic interpretability.
Inspect claims and provenance →
Polysemantic neurons
A source-bounded mechanism record for polysemantic neurons within mechanistic interpretability.
Inspect claims and provenance →
SAE encoder decoder
A source-bounded mechanism record for sae encoder decoder within mechanistic interpretability.
Inspect claims and provenance →
Causal scrubbing
A source-bounded method record for causal scrubbing within mechanistic interpretability.
Inspect claims and provenance →
In context learning circuits
A source-bounded method record for in context learning circuits within mechanistic interpretability.
Inspect claims and provenance →
Toy models of superposition
A source-bounded method record for toy models of superposition within mechanistic interpretability.
Inspect claims and provenance →
Below the public line
Draft inventory remains private until canonical release.
The public surface exposes aggregate capacity only. Draft identifiers, titles, routes, claims, source packets, and review blockers are excluded from crawlable pages and registries.
Withheld records
19
Withheld typed edges
22
Domain contract
The registry exposes the boundary, not just the content.
Graph records
30
Typed edges
34
Public canonical
11
Withheld
19
Read the governing architecture in the Epistemic Publication System.