© 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. 33895
    Prev
    Next
    INDEX
    Explanations

    license and project

    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
     Pry
    -0.10
    озд
    -0.09
    chai
    -0.09
    keit
    -0.08
    aron
    -0.08
     Rubber
    -0.08
     Gri
    -0.08
    iek
    -0.08
     reserv
    -0.08
    adia
    -0.08
    POSITIVE LOGITS
     bail
    0.10
    illet
    0.09
    sted
    0.09
    ASP
    0.09
     Tags
    0.09
     Corporate
    0.09
     shrinking
    0.09
     Bail
    0.09
     Lowest
    0.09
     oblig
    0.08
    Activations Density 0.002%

    No Known Activations