© 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. 29442
    Prev
    Next
    INDEX
    Explanations

    okio, okorie, okinawa, okajima, okeman

    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
     pray
    -0.09
    prech
    -0.08
    osti
    -0.08
    Prev
    -0.08
    ası
    -0.08
    este
    -0.08
    uggage
    -0.08
    esk
    -0.08
    iphy
    -0.08
     RT
    -0.08
    POSITIVE LOGITS
    tober
    0.11
     tg
    0.09
    ampa
    0.09
    oned
    0.09
    tern
    0.09
     acceler
    0.09
    (ok
    0.09
    -ok
    0.09
    arma
    0.08
    egment
    0.08
    Activations Density 0.013%

    No Known Activations