© 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. 111706
    Prev
    Next
    INDEX
    Explanations

    new york, statement, host, remedies

    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
     Shel
    -0.10
     Alto
    -0.10
    Leap
    -0.09
     resc
    -0.09
    sis
    -0.09
     Cooke
    -0.09
    QRS
    -0.09
     Bison
    -0.09
    unden
    -0.09
     &#
    -0.09
    POSITIVE LOGITS
     bara
    0.11
    kus
    0.09
     yaz
    0.08
     fab
    0.08
     rev
    0.08
    ku
    0.08
     heroic
    0.08
     breakdown
    0.08
    ifact
    0.08
     mug
    0.08
    Activations Density 0.029%

    No Known Activations