© 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. 25144
    Prev
    Next
    INDEX
    Explanations

    Pl words

    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
    Negative Logits
    eting
    -0.11
    eker
    -0.10
    esser
    -0.10
    ipel
    -0.09
    imson
    -0.09
    ernes
    -0.09
    usher
    -0.09
    eted
    -0.09
    lid
    -0.09
     impartial
    -0.09
    POSITIVE LOGITS
    a
    0.14
     Zuk
    0.10
    astr
    0.09
    ESP
    0.09
     nest
    0.09
     economists
    0.09
    aab
    0.09
    aos
    0.09
     Conrad
    0.09
     quotations
    0.09
    Activations Density 0.019%

    No Known Activations