© 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. 3421
    Prev
    Next
    INDEX
    Explanations

    reflexology

    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
     invaluable
    -0.09
     useful
    -0.08
    aca
    -0.08
     terrifying
    -0.08
     fantas
    -0.08
     tip
    -0.08
     cha
    -0.08
     Tip
    -0.08
    .
    -0.07
     fares
    -0.07
    POSITIVE LOGITS
     Urg
    0.10
    ERVER
    0.10
    WL
    0.10
     Seymour
    0.10
     Cler
    0.10
     contamin
    0.10
     NORMAL
    0.10
     Eden
    0.10
    VN
    0.10
     Normal
    0.10
    Activations Density 0.004%

    No Known Activations