© 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. 25034
    Prev
    Next
    INDEX
    Explanations

    questions like math problems

    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
     Tone
    -0.08
    ilter
    -0.08
     Conversation
    -0.08
     fa
    -0.08
     Telegraph
    -0.08
    cus
    -0.08
    aron
    -0.08
     Ire
    -0.08
     Convers
    -0.08
     conversation
    -0.08
    POSITIVE LOGITS
    rys
    0.09
    --[
    0.09
    ensch
    0.09
     Dys
    0.09
     âĨĴ↵↵
    0.09
     ry
    0.09
     endregion
    0.09
    avax
    0.09
    resh
    0.09
     Tri
    0.09
    Activations Density 0.325%

    No Known Activations