© 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. 87643
    Prev
    Next
    INDEX
    Explanations

    telling stories or information

    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
    uran
    -0.11
     Harper
    -0.10
     stamp
    -0.10
    [to
    -0.10
     emphasis
    -0.10
    arians
    -0.09
    cott
    -0.09
    oku
    -0.09
    undi
    -0.09
     Seed
    -0.09
    POSITIVE LOGITS
     tales
    0.12
     tale
    0.12
     story
    0.10
     jokes
    0.10
     goog
    0.10
    uten
    0.09
     STORY
    0.09
    stories
    0.09
    positor
    0.09
     stories
    0.09
    Activations Density 0.038%

    No Known Activations