© 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. 18406
    Prev
    Next
    INDEX
    Explanations

    questions followed by "ask" or "can"

    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
     wyn
    -0.09
     Rut
    -0.09
     helicopt
    -0.09
    -int
    -0.08
    midd
    -0.08
    405
    -0.08
    rij
    -0.08
     chambers
    -0.08
    404
    -0.08
    ÄĽ
    -0.08
    POSITIVE LOGITS
     ask
    0.34
     Ask
    0.27
     asks
    0.27
    Ask
    0.26
    ask
    0.24
    asks
    0.22
     asking
    0.22
     say
    0.20
    ?
    0.19
     Asking
    0.19
    Activations Density 0.112%

    No Known Activations