© 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. 50721
    Prev
    Next
    INDEX
    Explanations

    fifty million, percent, essays, year

    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
     liv
    -0.10
    sem
    -0.10
    onas
    -0.08
    yth
    -0.08
    oust
    -0.08
    oge
    -0.08
    ays
    -0.08
    heimer
    -0.08
    aries
    -0.08
     halfway
    -0.08
    POSITIVE LOGITS
     Shades
    0.19
     shades
    0.13
    лиÑĨ
    0.12
     Cent
    0.12
     caliber
    0.10
    uada
    0.10
    ãĥĪ
    0.09
    psilon
    0.09
     Cory
    0.09
     Shan
    0.09
    Activations Density 0.075%

    No Known Activations