© 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. 12288
    Prev
    Next
    INDEX
    Explanations

    learn more about

    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
    holm
    -0.09
    综åIJĪç´łè´¨
    -0.09
    èĹıçĿĢ
    -0.09
     ÙħÙĤ
    -0.08
    æĹ·
    -0.08
    uve
    -0.08
     Spr
    -0.08
    æĽ
    -0.08
    avan
    -0.08
    ctype
    -0.08
    POSITIVE LOGITS
    æĽ´å¤ļä¿¡æģ¯
    0.12
    详æĥħ
    0.12
    äºĨè§£æĽ´å¤ļ
    0.11
    ãģ«ãģ¤ãģĦãģ¦ãģ¯
    0.09
    äºĨ解
    0.09
    @c
    0.09
    羣缸
    0.09
    詳ãģĹãģı
    0.09
     подÑĢоб
    0.09
    åĬłçĽŁ
    0.09
    Activations Density 0.079%

    No Known Activations