© 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. 59376
    Prev
    Next
    INDEX
    Explanations

    the norm word marks title our

    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
     Fle
    -0.10
    ãģ¥
    -0.09
    urch
    -0.09
    è¿Ļä¹Łæĺ¯
    -0.09
    inker
    -0.09
    ä¸Ģ人
    -0.09
    æĽ´éĩįè¦ģ
    -0.09
     dụ
    -0.09
    ucken
    -0.08
    æ§İ
    -0.08
    POSITIVE LOGITS
    åĬ²
    0.11
    åĬ©
    0.10
    ä½Ĺ
    0.09
    èĬ±å¼Ģ
    0.09
    åĩĨåĪĻ
    0.09
    æŶå°ļ
    0.09
    é£İæ°Ķ
    0.09
    è½»æĿ¾
    0.09
    人éĹ´
    0.08
    äºĭåĬ¡
    0.08
    Activations Density 0.039%

    No Known Activations