© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33963
    Prev
    Next
    INDEX
    Explanations

    `United States` citations and `Apache License`

    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
    Negative Logits
    uye
    -0.09
     {(
    -0.09
    /is
    -0.08
     Rou
    -0.08
    rian
    -0.08
    azer
    -0.08
     Bod
    -0.08
    iversary
    -0.08
    ru
    -0.08
    pron
    -0.08
    POSITIVE LOGITS
     rub
    0.11
     VAN
    0.10
     pains
    0.09
     Budd
    0.09
     stalk
    0.09
     whip
    0.09
     GRA
    0.09
    rub
    0.09
     locally
    0.09
     <![
    0.09
    Activations Density 0.016%

    No Known Activations