© 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. 14245
    Prev
    Next
    INDEX
    Explanations

    compilation album, mixtape, or CD

    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
    alties
    -0.09
    anness
    -0.08
     Warfare
    -0.08
     doubling
    -0.08
    chrome
    -0.08
     comm
    -0.07
    est
    -0.07
     tern
    -0.07
    akin
    -0.07
     caut
    -0.07
    POSITIVE LOGITS
    ogue
    0.11
    ÑĮÑİ
    0.11
    tures
    0.11
    tee
    0.11
    odon
    0.10
     steward
    0.10
    ussen
    0.10
    Uvs
    0.10
    unexpected
    0.10
    .ext
    0.10
    Activations Density 0.005%

    No Known Activations