© 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. 113197
    Prev
    Next
    INDEX
    Explanations

    Caroline and Carolina names

    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
    enza
    -0.09
    ened
    -0.09
    ometrics
    -0.09
    лож
    -0.09
    resse
    -0.09
    akov
    -0.08
    lick
    -0.08
    ary
    -0.08
    ilyn
    -0.08
    icl
    -0.08
    POSITIVE LOGITS
    enment
    0.10
    ofs
    0.09
    ces
    0.09
    --[
    0.09
    irts
    0.09
    ingle
    0.09
     ashes
    0.09
    /trans
    0.09
    å¼ı
    0.08
     jihad
    0.08
    Activations Density 0.013%

    No Known Activations