© 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. 18542
    Prev
    Next
    INDEX
    Explanations

    dick's or names like dickson

    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
    ummer
    -0.08
    å¤
    -0.08
     chick
    -0.08
     graveyard
    -0.08
     cand
    -0.08
    zyst
    -0.08
     imposition
    -0.08
    /ap
    -0.08
     slic
    -0.08
    pages
    -0.08
    POSITIVE LOGITS
    ie
    0.15
    son
    0.15
    erson
    0.13
    enson
    0.12
    inson
    0.11
    ason
    0.11
     IE
    0.11
    tam
    0.10
    SON
    0.10
    eson
    0.10
    Activations Density 0.022%

    No Known Activations