© 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. 29983
    Prev
    Next
    INDEX
    Explanations

    button click

    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
    tractive
    -0.09
    ivamente
    -0.09
     Klopp
    -0.09
     då
    -0.09
     succesfully
    -0.09
    ilden
    -0.09
     Hubb
    -0.09
    vably
    -0.08
     reb
    -0.08
     herself
    -0.08
    POSITIVE LOGITS
    Ø©
    0.11
    а
    0.11
    a
    0.10
    ei
    0.10
    Ñĭ
    0.09
    us
    0.09
    en
    0.09
    -court
    0.09
    es
    0.09
    à¹Į
    0.09
    Activations Density 0.214%

    No Known Activations