TransformerLens
Vannus records that this vendor routes across several model providers — not captured by one. Every finding below is quoted to the vendor’s own document, or marked not disclosed where the vendor publishes nothing.
Mechanistic interpretability library — enables Activation Addition (ActAdd) by accessing transformer residual streams, computing steering vectors, and injecting them via forward hooks for real-time latent space steering
TransformerLens lets you load in 15,000+ open source language models across 140+ architecture families, and exposes the internal activations of the model to you.
Not yet assessed. We publish a sovereignty position only where the vendor documents one — we do not infer it from a domain or a company name.
Vannus publishes a nine-dimension trust framework — data sovereignty, training privacy, compliance posture, operational resilience, exit portability, and more. The heaviest criterion asks whether the tool builds its own AI or resells someone else's model; where the vendor discloses it, the grade cites the vendor's own documentation. No paid placements — scoring is walled off from affiliate revenue. See the methodology →