© 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. 46418
    Prev
    Next
    INDEX
    Explanations

    reload, refresh, compare

    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
     Salman
    -0.13
     Salisbury
    -0.12
     overwhelm
    -0.11
     enumerable
    -0.11
    abant
    -0.11
     intrusive
    -0.11
     Cara
    -0.11
    owi
    -0.11
     :↵↵↵↵
    -0.11
    spl
    -0.11
    POSITIVE LOGITS
     Dove
    0.07
     Char
    0.07
     Fischer
    0.07
    dup
    0.07
     Colo
    0.07
     Dane
    0.06
     voluntarily
    0.06
    ucker
    0.06
    .ident
    0.06
    artisan
    0.06
    Activations Density 0.001%

    No Known Activations