© 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. 14019
    Prev
    Next
    INDEX
    Explanations

    Category names

    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
    anonymous
    -0.10
    ...↵↵↵
    -0.09
     engr
    -0.09
    ....↵
    -0.09
     terrifying
    -0.09
    inue
    -0.09
    Slave
    -0.09
    Escort
    -0.09
     cricket
    -0.09
    ...↵
    -0.09
    POSITIVE LOGITS
     Caucasian
    0.11
     contemporary
    0.11
     indoors
    0.11
     newcomer
    0.10
     brunette
    0.10
     blonde
    0.10
     Contemporary
    0.10
     suspense
    0.10
     outsider
    0.10
     realism
    0.10
    Activations Density 0.084%

    No Known Activations