© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 47524
    Prev
    Next
    INDEX
    Explanations

    ethnic or national groups

    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
     thai
    -0.09
     Nigerian
    -0.08
    -mouth
    -0.08
    osit
    -0.08
    omers
    -0.08
    ennon
    -0.08
     Italian
    -0.08
     brazil
    -0.08
     Hait
    -0.08
     Bucc
    -0.08
    POSITIVE LOGITS
    -speaking
    0.24
    -American
    0.23
    -language
    0.20
    -Russian
    0.19
    -Americans
    0.18
    istan
    0.17
    apolis
    0.17
    ischer
    0.17
    isches
    0.16
    -Israel
    0.16
    Activations Density 0.377%

    No Known Activations