© 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. 6755
    Prev
    Next
    INDEX
    Explanations

    copy, use, Set, points, bowl, dropdown

    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
    404
    -0.11
    742
    -0.10
     updateTime
    -0.09
     Ivory
    -0.09
    loo
    -0.09
    601
    -0.09
     Jacques
    -0.09
     spine
    -0.08
    Tim
    -0.08
    legs
    -0.08
    POSITIVE LOGITS
     from
    0.11
     Proto
    0.10
    FromFile
    0.10
    ief
    0.10
    Desde
    0.09
     From
    0.09
    ä»İ
    0.09
     offline
    0.09
    Æ°á»
    0.09
    (using
    0.09
    Activations Density 0.006%

    No Known Activations