© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90690
    Prev
    Next
    INDEX
    Explanations

    ethnic and racial demographics

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Gingrich
    -0.09
    utar
    -0.08
    RIPT
    -0.08
    ghi
    -0.08
     Lenin
    -0.08
     Tasmania
    -0.08
     pij
    -0.08
     Gilles
    -0.07
     toddler
    -0.07
    اء
    -0.07
    POSITIVE LOGITS
     Asian
    0.27
     Chinese
    0.25
     African
    0.24
     Hispanic
    0.23
     Italian
    0.22
     Vietnamese
    0.21
     Mexican
    0.21
     Indian
    0.20
     Russian
    0.20
     Japanese
    0.20
    Activations Density 0.344%

    No Known Activations