Open-source EU AI Act Annex IV compliance toolkit. Mechanistic interpretability + circuit discovery for transformers. One function call generates a court-ready evidence package

Practical mechanistic interpretability tools — activation caching, linear probes, activation patching, circuit discovery, and visualization for transformer models

Mechanistic interpretability CLI for transformer models on Apple Silicon. Analyze per-layer predictions, monitor activation drift, compare models, discover circuits. MLX-based, no GPU needed.

A framework for identifying neural circuit components via convergent evidence across weight deltas, activations, and latent geometry.

Mechanistic interpretability and safety auditing for Decision Transformers. Features circuit mapping, causal patching, TopK SAEs, and behavioral steering.