© 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. 6231
    Prev
    Next
    INDEX
    Explanations

    as much

    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
    åģļæ³ķ
    -0.09
    æĭ¼
    -0.08
     Vig
    -0.08
    ignum
    -0.08
    离å¼ĢäºĨ
    -0.08
    [Math
    -0.08
    -pad
    -0.08
    atto
    -0.08
    åĽº
    -0.07
     HOL
    -0.07
    POSITIVE LOGITS
     equally
    0.13
    åIJĮçŃī
    0.13
    ä¸įä½İäºİ
    0.13
    ä¸Ģæł·
    0.12
    ä¸Ģæł·çļĦ
    0.12
    ä¸Ŀ毫ä¸į
    0.12
    åłª
    0.12
    ä¸Ģ樣
    0.12
    è¦ģæ¯Ķ
    0.12
    ä¸įå°ijäºİ
    0.11
    Activations Density 0.065%

    No Known Activations