- Conduid
- Marketplace
- #mechanistic-interpretability
MCP servers tagged mechanistic-interpretability
5 live MCP servers tagged "mechanistic-interpretability", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with mechanistic-interpretability.
Agent Template
🤖 Build multi-agent, retrieval-augmented AI workflows with ready-to-use components for document serving, Q/A bots, and agent orchestration.
Mercury MCP
Cross-architecture LLM internal observation database (23 models, 13 architecture families). Exposed as MCP tools for any AI coding agent.
Holonomy Lib
Research-grade PyTorch math: differential geometry, spectral graph theory, discrete Ricci flow, simplicial topology, persistent homology, cellular sheaves, SO(3) Lie primitives, i…
Dynolab
Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interventions with local inference, a Python SD…
Agent Template
🤖 Build multi-agent, retrieval-augmented AI workflows with ready-to-use components for document serving, Q/A bots, and agent orchestration.