Walkthrough - nnsight
nnsight.net · 5,419 words · saved by 1 readers
Documentation for the nnsight Python library
Info Last Execution: 2026-07-27 Package Version nnsight 0.8 Python 3.12.13 torch 2.13.0+cu126 transformers 5.15.0 The API for a transparent science on black-box AI¶ In this era of large-scale deep learning, the most interesting AI models are massive black boxes that are hard to run. Ordinary commercial inference service APIs let us interact with huge models, but they do not let us access model internals. The nnsight library is different: it provides full access to all neural network internals. When using nnsight together with a remote service like the National Deep Inference Fabric…
saved by
related reading
- nnsightnnsight.net
- Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
- Neuronpedianeuronpedia.org
- Transformer Circuits Threadtransformer-circuits.pub
- Together AI | The AI Native Cloudtogether.ai
- Goodfire AIgoodfire.ai
- Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activationstransformer-circuits.pub
- Transformer Explainer: LLM Transformer Model Visually Explainedpoloclub.github.io
- Interpretability Infrastructure at Frontier Scale: Harvesting Activations from a Trillion-Parameter Modelgoodfire.ai
- A Comprehensive Mechanistic Interpretability Explainer & Glossary — Neel Nandaneelnanda.io
- Topicslearnmechinterp.com
- Jacobian Lens – Qwen3.6-27B ｜ Neuronpedianeuronpedia.org