© 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. 47607
    Prev
    Next
    INDEX
    Explanations

    can also

    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
    ä¿¡å¾Ĵ
    -0.09
    MainThread
    -0.09
    姥
    -0.09
    ä¸įä½Ĩ
    -0.09
    大家ä¸Ģèµ·
    -0.09
    人æ°ijæľįåĬ¡
    -0.09
    eld
    -0.09
    prt
    -0.09
    .opts
    -0.08
    çļĦ对象
    -0.08
    POSITIVE LOGITS
    ä¹Łåı¯
    0.11
    ä¹Łåı¯ä»¥
    0.10
    çİ°åŃĺ
    0.10
     Также
    0.09
    also
    0.08
    ä¹Łæľī
    0.08
    ä¸įéĻIJ
    0.08
     also
    0.08
    ãĤĤãģ¡ãĤįãĤĵ
    0.08
    ä¸įæİĴéĻ¤
    0.08
    Activations Density 0.053%

    No Known Activations