© 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. 87961
    Prev
    Next
    INDEX
    Explanations

    book panel client particle Substance factory item column Magic Marker

    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
    ¤
    -0.07
    izia
    -0.07
    avras
    -0.06
    ữ
    -0.06
    atas
    -0.06
     Scott
    -0.06
     Wen
    -0.06
    etak
    -0.06
    idd
    -0.06
    uen
    -0.06
    POSITIVE LOGITS
    isman
    0.14
     Hammond
    0.13
    acier
    0.13
    ivist
    0.12
    cao
    0.12
    acle
    0.12
    ueue
    0.12
    icle
    0.12
    Ñĭй
    0.12
    orpion
    0.12
    Activations Density 3.679%

    No Known Activations