© 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. 87729
    Prev
    Next
    INDEX
    Explanations

    error rate, disease, cardiac failure, compatibility

    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
     Tol
    -0.10
     _______,
    -0.10
     &↵
    -0.08
    î
    -0.08
     Phillips
    -0.08
    -0.08
    habi
    -0.08
     representa
    -0.07
     misunder
    -0.07
    YRO
    -0.07
    POSITIVE LOGITS
    .↵↵
    0.24
    ...↵↵
    0.21
    ..↵↵
    0.20
    ,âĢ¦↵↵
    0.19
    ,...↵↵
    0.17
    âĢ¦↵↵
    0.16
     .↵↵
    0.16
     [âĢ¦]↵↵
    0.15
     ...↵↵
    0.15
    .↵
    0.15
    Activations Density 0.267%

    No Known Activations