© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 116203
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     answers
    -0.08
     lov
    -0.08
     Klein
    -0.08
    Ñij
    -0.08
     Pending
    -0.08
     TNT
    -0.08
     unmistak
    -0.08
    âĢ¦”↵↵
    -0.08
     Se
    -0.07
    äd
    -0.07
    POSITIVE LOGITS
     logging
    0.12
    Logger
    0.10
    logger
    0.10
    Jay
    0.10
    logging
    0.10
     Ced
    0.10
    /cache
    0.10
    odom
    0.10
    stag
    0.10
    ï¼IJ
    0.10
    Activations Density 0.000%

    No Known Activations