Circuit Tracer
Open-source tool for visualizing LLM internal computations
Visit Circuit Tracer →Circuit Tracer is an open-source library by Anthropic that helps researchers understand how large language models process information by generating attribution graphs of internal computations. It can be used via the Neuronpedia web interface or as a standalone Python library. The tool is aimed at AI interpretability researchers seeking transparency into model behavior.
At a glance
Capabilities
Categories
Alternatives
For AI agents: machine-readable markdown version of this page at
/tools/circuit-tracer.md,
or send Accept: text/markdown.