© 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. 6780
    Prev
    Next
    INDEX
    Explanations

    quotation marks followed by capitalization

    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
    .Bottom
    -0.11
    cas
    -0.10
    ...]↵↵
    -0.09
    ickle
    -0.09
     Crud
    -0.09
     Ged
    -0.09
     ks
    -0.09
    _tran
    -0.09
     Surely
    -0.09
     beats
    -0.09
    POSITIVE LOGITS
    We
    0.11
    ,”
    0.10
     We
    0.10
     we
    0.10
    There
    0.10
     ,"
    0.10
    Initially
    0.09
     Initially
    0.09
     everybody
    0.09
    "[
    0.09
    Activations Density 0.069%

    No Known Activations