© 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. 46098
    Prev
    Next
    INDEX
    Explanations

    needs police coronavirus trial level silicon current

    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
     proverb
    -0.10
     womens
    -0.10
     spiel
    -0.10
     swell
    -0.09
     offending
    -0.09
     carn
    -0.09
     teen
    -0.09
     blooms
    -0.08
     stor
    -0.08
     operative
    -0.08
    POSITIVE LOGITS
     opponent
    0.14
    anine
    0.12
     whole
    0.10
    owi
    0.10
     two
    0.10
     entire
    0.10
     ya
    0.10
    kie
    0.10
     Quart
    0.10
    ’T
    0.10
    Activations Density 0.212%

    No Known Activations