© 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. 46658
    Prev
    Next
    INDEX
    Explanations

    movement and speed

    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
    .adv
    -0.10
    xo
    -0.09
     Kay
    -0.09
     Kirk
    -0.09
     dense
    -0.09
     ADV
    -0.09
     incom
    -0.09
     Harding
    -0.09
    alon
    -0.09
    hee
    -0.09
    POSITIVE LOGITS
     movements
    0.19
     swift
    0.18
     motions
    0.16
     quick
    0.15
     movement
    0.15
     jer
    0.15
     practiced
    0.15
     gesture
    0.15
     slow
    0.15
     maneuver
    0.14
    Activations Density 0.046%

    No Known Activations