© 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. 29789
    Prev
    Next
    INDEX
    Explanations

    legal phrases and conditions

    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
    ajas
    -0.12
     toll
    -0.12
    aż
    -0.12
    adors
    -0.12
    aeda
    -0.12
     fines
    -0.11
    \a
    -0.11
    ;]/
    -0.11
    atto
    -0.11
    odash
    -0.11
    POSITIVE LOGITS
     frank
    0.08
     curb
    0.07
     Franklin
    0.06
    Â
    0.06
    <|fim_middle|>
    0.06
     deb
    0.06
    235
    0.06
    mans
    0.06
     Ele
    0.06
     saber
    0.06
    Activations Density 0.001%

    No Known Activations