© 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. 92327
    Prev
    Next
    INDEX
    Explanations

    .json or values

    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
    Toolkit
    -0.10
    zap
    -0.10
     BU
    -0.10
     Kap
    -0.09
     capacity
    -0.09
     Wilkinson
    -0.09
    Ĥ¬
    -0.09
    815
    -0.09
    .KeyEvent
    -0.09
     âĢ¦.
    -0.09
    POSITIVE LOGITS
    č↵↵
    0.11
    .↵↵
    0.09
     .↵↵
    0.09
    <|endoftext|>
    0.08
    ).↵↵
    0.08
    ãĢĤ↵↵
    0.08
    ↵↵
    0.08
    ,.↵↵
    0.08
    ...↵↵
    0.08
    ãĢģ↵↵
    0.08
    Activations Density 0.001%

    No Known Activations