© 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. 28655
    Prev
    Next
    INDEX
    Explanations

    zip and zipper related terms

    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
    erten
    -0.09
     Scri
    -0.08
    iego
    -0.08
    aly
    -0.08
     pumped
    -0.08
    .blit
    -0.08
     Rede
    -0.08
     lean
    -0.08
    sheet
    -0.08
     batter
    -0.08
    POSITIVE LOGITS
    /button
    0.16
    pered
    0.13
    /buttons
    0.12
     unzip
    0.11
     opening
    0.10
    /slider
    0.10
    /bind
    0.10
    pering
    0.10
    etta
    0.10
    /watch
    0.10
    Activations Density 0.007%

    No Known Activations