© 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. 45977
    Prev
    Next
    INDEX
    Explanations

    eating and meals

    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
     DIY
    -0.11
    azen
    -0.10
    ather
    -0.10
    390
    -0.10
    alf
    -0.10
     Vern
    -0.09
    ilent
    -0.09
     Ire
    -0.09
    irse
    -0.09
    ogle
    -0.09
    POSITIVE LOGITS
     disorders
    0.11
     disorder
    0.10
     differently
    0.10
     healthier
    0.10
     psychology
    0.10
     Psychology
    0.10
     Disorders
    0.09
    /chart
    0.09
     less
    0.09
     establishment
    0.09
    Activations Density 0.007%

    No Known Activations