© 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. 59106
    Prev
    Next
    INDEX
    Explanations

    Yang style Tai Chi Chuan names

    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
    ä»»æĢ§
    -0.10
    èĦijè¢ĭ
    -0.09
     поÑģк
    -0.08
    å¤ı
    -0.08
     Kut
    -0.08
    溢
    -0.08
    æºľ
    -0.08
    稳
    -0.08
    æĿŁç¼ļ
    -0.08
     <![
    -0.08
    POSITIVE LOGITS
    ä¸Ģ代
    0.11
    幡
    0.10
    ãn
    0.10
    æŀ¶åŃIJ
    0.10
    åįıä¼ļä¼ļéķ¿
    0.09
    åIJį家
    0.09
    éĬ®
    0.09
    å¼ŁåŃIJ
    0.09
    à¸Ļà¸Ńà¸ģ
    0.09
    åĪĨæĶ¯
    0.09
    Activations Density 0.017%

    No Known Activations