Getting started with Aquin CLI

Aquin is a CLI for mechanistic interpretability and model analysis on your own GPU. You install aquin on a CUDA machine, connect a session, load a model, and run inspections, simulations, and evals from the terminal. Every result mirrors live to the web dashboard at aquin.app: same session, same cards, no re-upload.

The CLI is not a hosted GPU service. Your machine runs forward passes locally. The cloud only syncs state: messages, tool results, and session memory stream over SSE to the orchestrator panel. Use aquin chat for a multi-turn agent, or invoke any tool directly as a one-shot command.

Tool mode switches automatically when you load a model. Load an LLM (GPT-2, Pythia, Llama) and you get inspection, eval, and simulation commands. Load an embedding encoder (GTE, MiniLM, BGE) and you get the embed analysis suite. No manual mode toggle; aquin help always shows what is available for your current session.

Feature-level tools need a sparse autoencoder pulled locally first (aquin pull sae gpt2-small-l8). The sidebar groups every command by category (inspection, SAE inspection, simulation, evals), split by LLM and embedding. Cross-cutting setup lives under Agent & raw CLI.

First session

What to read next

• Agent & raw CLI: connect, load, chat, configuration, shared flags
• Inspection (LLM): attention, perturbation, weight health
• Inspection SAE (LLM): inspect, steer, feature analysis
• Simulation (LLM): training forecast before you commit GPU cycles