© 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. 30406
    Prev
    Next
    INDEX
    Explanations

    http:// URLs

    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
    EDA
    -0.11
     unrelated
    -0.11
     Lancaster
    -0.11
    CEED
    -0.10
    wid
    -0.10
    unfinished
    -0.09
     ([[
    -0.09
    --[
    -0.09
    selector
    -0.09
    lander
    -0.09
    POSITIVE LOGITS
     drill
    0.08
     watt
    0.08
     Fres
    0.08
     conserv
    0.08
     tactical
    0.07
     Fiscal
    0.07
     nas
    0.07
     Watt
    0.07
     glare
    0.07
     stroke
    0.07
    Activations Density 0.001%

    No Known Activations