© 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. 15488
    Prev
    Next
    INDEX
    Explanations

    numbered lists section identifiers

    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
    aha
    -0.10
    ritch
    -0.08
    azon
    -0.08
    enge
    -0.08
    owed
    -0.08
     Pont
    -0.08
    ieg
    -0.08
     Disconnect
    -0.08
     Higgins
    -0.08
    yc
    -0.07
    POSITIVE LOGITS
     aka
    0.10
    ukan
    0.10
     done
    0.10
     suited
    0.09
    /sp
    0.09
    aka
    0.09
    ÃŁ
    0.09
    EOS
    0.09
     spree
    0.09
     invent
    0.09
    Activations Density 0.585%

    No Known Activations