© 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. 18366
    Prev
    Next
    INDEX
    Explanations

    Texas, Indiana, Weinstein, argv

    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
     agendas
    -0.08
    etch
    -0.08
    inous
    -0.07
    enda
    -0.07
     Lansing
    -0.06
     treason
    -0.06
     ses
    -0.06
     FM
    -0.06
     incub
    -0.06
    æĸĻ
    -0.06
    POSITIVE LOGITS
     chop
    0.11
    amma
    0.11
    <hr
    0.11
    orget
    0.11
    anter
    0.10
    aire
    0.10
     Ted
    0.10
     Nearby
    0.10
     Guy
    0.10
    frei
    0.10
    Activations Density 0.001%

    No Known Activations