© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29741
    Prev
    Next
    INDEX
    Explanations

    ethnic minorities, communities, groups

    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
    arius
    -0.10
    çĹĽ
    -0.10
    æĸ°é¢ĸ
    -0.09
    çĭ¬ç«ĭ
    -0.09
    奥巴
    -0.09
    åĿª
    -0.09
     Trilogy
    -0.08
    æĽĿ
    -0.08
    rlen
    -0.08
    ãĥĥãĤ¯
    -0.08
    POSITIVE LOGITS
    è¶´åľ¨
    0.10
    失è°ĥ
    0.10
    åIJĦçľģ
    0.09
    å°ijæķ°æ°ijæĹı
    0.09
    gra
    0.09
     assim
    0.09
    缸å¤Ħ
    0.09
    .eth
    0.09
    dp
    0.09
    é¦ħ
    0.08
    Activations Density 0.058%

    No Known Activations