© 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. 47579
    Prev
    Next
    INDEX
    Explanations

    as directed by

    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
     Rif
    -0.09
    raq
    -0.08
    uant
    -0.08
    å¾ģæĪĺ
    -0.08
    äºļ太
    -0.08
    女æĺŁ
    -0.08
    糧
    -0.08
    åĸĦäºİ
    -0.08
    æ´»åĬ¨ä¸Ń
    -0.08
    .FileSystem
    -0.08
    POSITIVE LOGITS
     اÙĦتاب
    0.09
    绵
    0.08
    鸡
    0.08
    ãģĦãģĭ
    0.08
    лÑij
    0.08
    è¡Ķ
    0.08
    æİĤ
    0.08
    åijĬè¯ī大家
    0.08
    æĥ¯
    0.08
    å¯¹æľªæĿ¥
    0.08
    Activations Density 0.007%

    No Known Activations