© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30738
    Prev
    Next
    INDEX
    Explanations

    Asian Pacific Americans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
     Liv
    -0.09
    åĴ¬
    -0.09
    èį·
    -0.09
    派人
    -0.09
    æĴĴ
    -0.09
    åĭĥ
    -0.08
    åıĸæļĸ
    -0.08
    诰
    -0.08
     Deliver
    -0.08
    éĽĢ
    -0.08
    POSITIVE LOGITS
     Pacific
    0.12
    Pacific
    0.11
     Hawaii
    0.11
     Asian
    0.11
     Pac
    0.11
     Hawaiian
    0.10
    apons
    0.10
    åľ¨é¦Ļ港
    0.10
    -Pacific
    0.10
    åľ¨æĹ¥æľ¬
    0.09
    Activations Density 0.129%

    No Known Activations