© 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. 50724
    Prev
    Next
    INDEX
    Explanations

    change or end

    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
    osas
    -0.11
    .fin
    -0.10
     Dire
    -0.10
     Carson
    -0.10
    779
    -0.10
     Gle
    -0.10
    (fin
    -0.09
     Canton
    -0.09
    escal
    -0.09
    etat
    -0.09
    POSITIVE LOGITS
     reconsider
    0.15
     rethink
    0.15
     invol
    0.12
     momentarily
    0.11
     prematurely
    0.11
     temporarily
    0.11
    Filed
    0.10
     lose
    0.10
     crave
    0.10
     improperly
    0.09
    Activations Density 0.068%

    No Known Activations