© 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. 34204
    Prev
    Next
    INDEX
    Explanations

    skin cancer, telephone number, metabolic syndrome

    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
    osci
    -0.10
     KN
    -0.10
    zens
    -0.09
    iez
    -0.09
    arb
    -0.09
     neckline
    -0.09
    usz
    -0.09
     invol
    -0.09
    iets
    -0.08
    agements
    -0.08
    POSITIVE LOGITS
     itself
    0.12
     proper
    0.09
     dire
    0.09
    peater
    0.09
     pride
    0.09
     Hammond
    0.09
     beste
    0.09
     #'
    0.08
     doub
    0.08
    -with
    0.08
    Activations Density 2.583%

    No Known Activations