© 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. 3362
    Prev
    Next
    INDEX
    Explanations

    fedex, frozen, movie

    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
    alk
    -0.09
     Morning
    -0.09
     Wald
    -0.08
    ubo
    -0.08
     Mess
    -0.08
    illed
    -0.08
     gauss
    -0.08
     spit
    -0.08
    ropic
    -0.08
    allen
    -0.08
    POSITIVE LOGITS
     Sky
    0.11
    loser
    0.11
    lator
    0.10
     reluct
    0.10
     aval
    0.10
    ([('
    0.10
     Avery
    0.10
    Chr
    0.10
     acupuncture
    0.10
    GI
    0.09
    Activations Density 0.002%

    No Known Activations