© 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. 24994
    Prev
    Next
    INDEX
    Explanations

    Kervella, Enqvist, Kildow, Kremenchutzky, Kefauver

    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
     Fade
    -0.10
     wrought
    -0.09
    ijo
    -0.08
    -sort
    -0.08
     Nest
    -0.08
     bere
    -0.08
     Bauer
    -0.08
    /OR
    -0.08
    -blue
    -0.08
    axy
    -0.08
    POSITIVE LOGITS
     Keywords
    0.08
     critique
    0.08
    lds
    0.08
    -keys
    0.08
    visibility
    0.08
     Bones
    0.08
    illes
    0.08
     Posted
    0.08
     knocking
    0.08
     tokenize
    0.08
    Activations Density 0.132%

    No Known Activations