© 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. 7460
    Prev
    Next
    INDEX
    Explanations

    products or services followed by 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
     cotton
    -0.09
    Gram
    -0.08
     Epid
    -0.08
    Âł
    -0.08
    mux
    -0.08
     Imam
    -0.08
    ternal
    -0.08
     correction
    -0.08
    urr
    -0.08
     mosque
    -0.08
    POSITIVE LOGITS
     heroine
    0.12
     #-
    0.10
    {/*
    0.10
    ugg
    0.10
     timed
    0.10
     protagonist
    0.10
    :!
    0.09
    /Index
    0.09
    abilities
    0.09
     transpose
    0.09
    Activations Density 0.006%

    No Known Activations