# Drowse | Local LLM interpretability and activation steering

Drowse is an open-source and fully local AI mechanistic interpretability workbench that works fully in your browser. Use Drowse to research large language models, inspect predictions and change an LLMs internal activity.

Drowse is an open-source workbench for mechanistic interpretability, activation steering, and local inference with language models. Run a compatible model in your browser, inspect tokens and internal representations, and compare how an intervention changes its output. A separate Python library and server support programmatic experiments.

- [Activation steering](https://drowse.ai/learn/activation-steering.md): Explore concept vectors, manifolds, feature steering, and probe gates.
- [Inspect language models](https://drowse.ai/learn/interpretability.md): Read token probabilities, concept probes, sparse features, and layer predictions.
- [Run a model in your browser](https://drowse.ai/learn/browser-models.md): Check WebGPU requirements, model choices, downloads, and local storage.
- [Compare experiments](https://drowse.ai/learn/experiments.md): Use branching conversations, token forks, and restricted-choice scoring.
- [Developers and browser agents](https://drowse.ai/developers.md): Discover WebMCP tools and the separate Python, OpenAI-compatible, and Ollama-compatible APIs.
- [Privacy and local data](https://drowse.ai/privacy.md): Understand what stays on your device and which actions make network requests.

[Open Drowse](https://drowse.ai/app) · [About and source](https://drowse.ai/about.md) · [Privacy and data storage](https://drowse.ai/privacy.md)