© 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. 18746
    Prev
    Next
    INDEX
    Explanations

    country, people, and traditions

    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
    vented
    -0.11
     scheduled
    -0.11
     stationary
    -0.10
     Odd
    -0.10
     ejaculation
    -0.10
     occult
    -0.10
     messy
    -0.10
    uds
    -0.10
     inde
    -0.10
     disgusting
    -0.10
    POSITIVE LOGITS
     stereotype
    0.14
     UNESCO
    0.13
     inherit
    0.13
     typically
    0.13
     distinctive
    0.12
     often
    0.12
     traditionally
    0.12
     beauty
    0.12
     tradition
    0.11
     stereotypes
    0.11
    Activations Density 0.028%

    No Known Activations