© 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. 30174
    Prev
    Next
    INDEX
    Explanations

    unsigned short uint

    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
     fir
    -0.09
     Fir
    -0.09
    <!--
    -0.09
    lich
    -0.08
    aus
    -0.08
    localized
    -0.08
     usu
    -0.08
    readcrumbs
    -0.08
    liner
    -0.08
    fen
    -0.08
    POSITIVE LOGITS
     enth
    0.09
     COURT
    0.09
    .hs
    0.09
     ramp
    0.09
    affen
    0.09
    rzy
    0.09
    ookie
    0.09
     Walton
    0.09
    antal
    0.09
    ynn
    0.09
    Activations Density 0.013%

    No Known Activations