© 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. 12358
    Prev
    Next
    INDEX
    Explanations

    other people

    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
    åĶ¯
    -0.09
    æ°ĶåĬ¿
    -0.09
    诱人
    -0.08
    asts
    -0.08
    åłª
    -0.08
    ashing
    -0.08
    YG
    -0.08
    è¿ĺæĺ¯ä¼ļ
    -0.08
     SES
    -0.08
     Osw
    -0.08
    POSITIVE LOGITS
    主管
    0.10
    ä½Ĩæĺ¯æĪij
    0.10
    erp
    0.10
    ä¸įåİ»
    0.09
    æ·±çŁ¥
    0.09
    åĿIJèIJ½
    0.09
    åIJĮå¿Ĺ
    0.09
    ä¸įå¾Ĺ转载
    0.09
    æĹ¥äº§
    0.09
    åIJĮäºĭ
    0.09
    Activations Density 0.047%

    No Known Activations