© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29198
    Prev
    Next
    INDEX
    Explanations

    direction of motion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     near
    -0.10
    éri
    -0.09
    eve
    -0.09
     Alb
    -0.09
     rein
    -0.08
     ginger
    -0.08
     replay
    -0.08
     Pang
    -0.08
     wrapper
    -0.08
    Tap
    -0.08
    POSITIVE LOGITS
     direction
    0.41
     Direction
    0.32
    Direction
    0.29
    direction
    0.29
     directions
    0.27
    -direction
    0.24
    _direction
    0.23
    .direction
    0.23
     directional
    0.22
     Directions
    0.21
    Activations Density 0.382%

    No Known Activations