© 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. 14150
    Prev
    Next
    INDEX
    Explanations

    the Apache License

    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
     Coc
    -0.08
    -hidden
    -0.08
    fell
    -0.08
    alth
    -0.07
     Fon
    -0.07
     dens
    -0.07
     Girlfriend
    -0.07
    wing
    -0.07
     coco
    -0.07
     rend
    -0.07
    POSITIVE LOGITS
     resp
    0.13
     diplom
    0.11
     Lester
    0.11
    izza
    0.10
     purpose
    0.10
    aja
    0.10
     journalistic
    0.10
    acon
    0.09
    ait
    0.09
     possibilities
    0.09
    Activations Density 0.006%

    No Known Activations