© 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. 111453
    Prev
    Next
    INDEX
    Explanations

    written sources, capabilities, typically large, cross-over, poly

    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
    Negative Logits
     Vine
    -0.11
    lbrace
    -0.10
    cba
    -0.10
    gra
    -0.10
     #####
    -0.09
    elter
    -0.09
    Guy
    -0.09
     Macros
    -0.09
    ICA
    -0.09
    -Za
    -0.09
    POSITIVE LOGITS
     tot
    0.10
    Uvs
    0.10
    ëĵ
    0.09
     bass
    0.08
     <↵
    0.08
     Bass
    0.08
    (click
    0.08
     alto
    0.07
     Benson
    0.07
     KR
    0.07
    Activations Density 0.011%

    No Known Activations