© 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. 47425
    Prev
    Next
    INDEX
    Explanations

    Wall Street Journal

    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
    们
    -0.10
    åĴĮåıijå±ķ
    -0.09
    ä¸İåıijå±ķ
    -0.09
    ä½ĵåĨħ
    -0.09
    山顶
    -0.09
    æijĨ
    -0.08
    enate
    -0.08
    äºĭä¸ļåıijå±ķ
    -0.08
    ãģįãģ¡ãĤĵãģ¨
    -0.08
    icare
    -0.08
    POSITIVE LOGITS
    è¯Ŀ说
    0.10
    ä¸Ģçľĭ
    0.10
    åĮ£
    0.10
    åĬĽéĩı
    0.10
    ToLocal
    0.09
    å¨ĺ
    0.09
    çıª
    0.09
    佬
    0.09
    ills
    0.09
    itzer
    0.09
    Activations Density 0.002%

    No Known Activations