© 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. 117252
    Prev
    Next
    INDEX
    Explanations

    seeing and noting

    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
     ber
    -0.10
    odings
    -0.10
    ocr
    -0.10
     apart
    -0.09
    abet
    -0.09
     aloud
    -0.09
    ilog
    -0.09
     prospects
    -0.09
     Ras
    -0.09
     Ging
    -0.09
    POSITIVE LOGITS
     notice
    0.10
    ctp
    0.10
     NOTICE
    0.10
     noticing
    0.10
     reco
    0.10
     blush
    0.10
     Amend
    0.09
     incident
    0.09
     indis
    0.09
     dele
    0.09
    Activations Density 0.011%

    No Known Activations