© 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. 3423
    Prev
    Next
    INDEX
    Explanations

    Mazzone, Mazda, Manteca

    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
    ç¦
    -0.09
    vet
    -0.09
     liqu
    -0.09
     Hampton
    -0.09
    nh
    -0.09
     foss
    -0.09
    bus
    -0.08
     glove
    -0.08
    /software
    -0.08
     partic
    -0.08
    POSITIVE LOGITS
    Pane
    0.11
     meg
    0.09
     Neighborhood
    0.09
    STDOUT
    0.09
    etti
    0.09
    consult
    0.09
    Armor
    0.09
    KI
    0.09
     mam
    0.09
    umbai
    0.09
    Activations Density 0.008%

    No Known Activations