© 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. 26530
    Prev
    Next
    INDEX
    Explanations

    motion and movement

    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
     trunk
    -0.12
     drainage
    -0.11
     Drain
    -0.11
     shred
    -0.11
     Tent
    -0.11
     distorted
    -0.10
     hob
    -0.10
     Redistribution
    -0.10
     pac
    -0.10
     trunc
    -0.10
    POSITIVE LOGITS
     movement
    0.23
     moving
    0.23
     mover
    0.23
     move
    0.20
     movers
    0.20
     Moving
    0.20
     moves
    0.19
    -moving
    0.19
     Move
    0.19
     Movement
    0.19
    Activations Density 1.469%

    No Known Activations