© 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. 31215
    Prev
    Next
    INDEX
    Explanations

    Disambiguation pages

    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
     Perc
    -0.08
     pec
    -0.08
     Geneva
    -0.08
     Caesar
    -0.08
     Freund
    -0.07
     apr
    -0.07
    ipa
    -0.07
     belle
    -0.07
     bell
    -0.07
     Gal
    -0.07
    POSITIVE LOGITS
    Sizer
    0.11
    /msg
    0.10
     atleast
    0.10
    Crud
    0.10
    standen
    0.10
    AY
    0.09
    /q
    0.09
    ollywood
    0.09
    unday
    0.09
    inality
    0.09
    Activations Density 0.070%

    No Known Activations