© 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. 89536
    Prev
    Next
    INDEX
    Explanations

    coach, officer, artist

    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
    elda
    -0.10
     dom
    -0.09
    atar
    -0.09
    undo
    -0.09
     Guth
    -0.09
    ondo
    -0.08
     nowhere
    -0.08
    urv
    -0.08
    undy
    -0.08
     operative
    -0.08
    POSITIVE LOGITS
    iders
    0.11
     clr
    0.10
    chet
    0.09
    ãģĹãģ¦
    0.08
     dere
    0.08
    pis
    0.08
     sagt
    0.08
    codes
    0.08
    arin
    0.08
    clr
    0.08
    Activations Density 0.002%

    No Known Activations