© 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. 47577
    Prev
    Next
    INDEX
    Explanations

    Hong Kong and East Asia

    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
    Negative Logits
    毡
    -0.11
    éĺ¿å¯Įæ±Ĺ
    -0.11
    课é¢ĺ
    -0.10
    éĩĩæļĸ
    -0.10
     Colorado
    -0.09
    lyn
    -0.09
    æ²®
    -0.09
     Raqqa
    -0.09
    oust
    -0.09
    resco
    -0.09
    POSITIVE LOGITS
     Hong
    0.12
     Taiwanese
    0.12
    æĺ¯éŁ©åĽ½
    0.12
    éŁ©åĽ½
    0.12
    Hong
    0.12
     Koreans
    0.12
    æĸ°åĬłåĿ¡
    0.12
     Singapore
    0.11
     Korean
    0.11
    åľ¨é¦Ļ港
    0.11
    Activations Density 0.209%

    No Known Activations