© 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. 29557
    Prev
    Next
    INDEX
    Explanations

    if I/we/you asked

    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
    æĺ¯ä¸Ģä½į
    -0.09
    æīįç®Ĺ
    -0.09
    èĪģ
    -0.09
    æ¾Ī
    -0.08
    大å¤ļ
    -0.08
    ivet
    -0.08
    ç»Ļä½łä»¬
    -0.08
    دÙĤ
    -0.08
    æ¯ıä¸Ģ次
    -0.08
    åĿ³
    -0.08
    POSITIVE LOGITS
    æĦ¿æĦı
    0.15
    æľī没æľī
    0.14
    é¡ĺæĦı
    0.11
    æĦıåIJij
    0.10
    帮å¿Ļ
    0.10
    æĺ¯åIJ¦æľī
    0.10
    æĦ¿
    0.09
    èĥ½åľ¨
    0.09
     willing
    0.09
    å¼ĥ
    0.09
    Activations Density 0.030%

    No Known Activations