© 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. 87660
    Prev
    Next
    INDEX
    Explanations

    died of illness or accident

    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
    HIR
    -0.10
    hip
    -0.10
     seriousness
    -0.09
     curs
    -0.09
    oft
    -0.09
    ritz
    -0.09
    rupt
    -0.09
     Kund
    -0.09
    eland
    -0.09
    osis
    -0.09
    POSITIVE LOGITS
     freak
    0.13
     sleeper
    0.10
     drug
    0.10
     unfore
    0.10
     randomly
    0.09
     unexpected
    0.09
    /random
    0.09
     inexp
    0.09
     cancer
    0.09
     silly
    0.09
    Activations Density 0.071%

    No Known Activations