Inference Tracer
ActiveA lightweight tool for tracing and visualizing token-by-token generation across model runs. Useful for understanding where attention concentrates during reasoning chains.
Python LLM observability
Source
Things built and in progress.
A lightweight tool for tracing and visualizing token-by-token generation across model runs. Useful for understanding where attention concentrates during reasoning chains.
Watches production data pipelines for structural changes and surfaces diffs in a clean terminal UI before they propagate downstream.