© 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. 92559
    Prev
    Next
    INDEX
    Explanations

    Bangladeshi locations

    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
     *[
    -0.10
    etine
    -0.10
    exion
    -0.10
    gow
    -0.10
    ippi
    -0.10
    urent
    -0.10
     Downs
    -0.10
    ENCY
    -0.10
     Strip
    -0.10
    ilenames
    -0.09
    POSITIVE LOGITS
    asser
    0.11
     drums
    0.11
     drum
    0.10
    alore
    0.10
     bang
    0.10
     ugl
    0.10
     Drum
    0.10
    ladesh
    0.09
     Wagner
    0.09
    -on
    0.09
    Activations Density 0.012%

    No Known Activations