© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5526
    Prev
    Next
    INDEX
    Explanations

    copending, copes, Copeland

    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
    ivities
    -0.10
    ANNER
    -0.09
    ished
    -0.09
     Exped
    -0.09
    itures
    -0.09
    ificant
    -0.09
    ivre
    -0.09
     stringstream
    -0.08
    ancement
    -0.08
    uw
    -0.08
    POSITIVE LOGITS
     cop
    0.22
     Cop
    0.21
    cop
    0.19
    /cop
    0.19
    eland
    0.17
    ious
    0.17
    Cop
    0.16
     coping
    0.14
    .deepcopy
    0.13
     cope
    0.13
    Activations Density 0.021%

    No Known Activations