mechanistic-interpretability
PackAI & modelsLets your agent inspect neural network internals to see how a model computes its answers.
Unavailable. Delivery for this kind is on the roadmap — not serving yet.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
About this app
Neural network interpretability tools including TransformerLens, SAELens, NNSight, and pyvene. Use when analyzing model internals, finding circuits, or understanding how models compute.
Signals
- GitHub stars
- 13k
- Forks
- 931
- Last commit
- Jun 2026
Advanced
- Item type
- plugin
- Key
orchestra-research-ai-research-skills-mechanistic-in-082imyb- Source
- github.com/orchestra-research/ai-research-skills