Skip to content
∑ Praveen T N Learning Library
Overview Concepts Flashcards Writing AI Feed Graph
Portfolio ↗
Overview Concepts Flashcards Writing AI Feed Graph Search Back to portfolio ↗
Library/ Writing/Tagged “mech-interp”

Tagged “mech-interp”

1 posts.

Clear
All Model Architecture14 Training & Alignment14 Inference & Serving12 Agents & Orchestration11 Reasoning & Evaluation9 Safety, Security & Governance3 Platforms & Practice12
Reasoning & Evaluation 23 min

From Features to Circuits: What Attribution Graphs Explain, and the Fraction They Do Not

Swap the Texas features for British Columbia and Claude answers Victoria instead of Austin. That single intervention is the strongest evidence yet that a language model performs genuine multi-step reasoning inside one forward pas…

interpretability mech-interp safety alignment ∑ ◫
The library

512 concepts, 3,886 flashcards and 75 long-form pieces on AI, NLP, deep learning, LLMs and agentic systems. Free, no sign-up, no paywall.

Sections Concepts Flashcards Writing AI Feed Knowledge Graph
Elsewhere Portfolio RSS LinkedIn Buy me a coffee

Written and maintained by Praveen T N.

© 2026 Praveen T N