© 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. 87927
    Prev
    Next
    INDEX
    Explanations

    Morning phrases

    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
    ters
    -0.12
    pery
    -0.11
    per
    -0.10
    /remove
    -0.10
    eral
    -0.10
    .addHandler
    -0.09
    amin
    -0.09
    holding
    -0.09
    ging
    -0.09
    ched
    -0.09
    POSITIVE LOGITS
    long
    0.10
     glory
    0.10
    .Formatter
    0.10
    mute
    0.10
    à§įà¦
    0.09
    /up
    0.09
     Glory
    0.09
     Blitz
    0.09
    iero
    0.09
    iglia
    0.09
    Activations Density 0.010%

    No Known Activations