© 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. 29478
    Prev
    Next
    INDEX
    Explanations

    target demographics and audiences

    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
    大家éĥ½åľ¨
    -0.09
    大家åı¯ä»¥
    -0.09
    æł¹æį®ä¸įåIJĮ
    -0.09
    loe
    -0.09
    ä¿Ł
    -0.09
    è¾ħ导
    -0.09
    .GetService
    -0.09
     ожи
    -0.09
    赢家
    -0.09
    iners
    -0.09
    POSITIVE LOGITS
    è¿Ļéĥ¨åĪĨ
    0.11
    æ½ľåľ¨
    0.10
    enso
    0.09
    åįłé¢Ĩ
    0.09
    éļĻ
    0.09
    è§Ĭ
    0.09
    æĶ¶åī²
    0.09
    è¿Ļä¸Ģ
    0.09
    ä¸ºçĽ®æłĩ
    0.08
    è¿ĩåİ»
    0.08
    Activations Density 0.053%

    No Known Activations