© 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. 16626
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with parentheses and exponents

    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
    ãģĿãģĹãģ¦
    -0.11
     ÑĦоÑĢ
    -0.09
    bolt
    -0.09
    gin
    -0.09
     Iso
    -0.08
    袤
    -0.08
    âĢ¢↵↵
    -0.08
    å°¤åħ¶æĺ¯åľ¨
    -0.08
    OTES
    -0.08
    qing
    -0.08
    POSITIVE LOGITS
    ä¼ģä¸ļæıIJä¾Ľ
    0.09
    _TYP
    0.08
    槽
    0.08
    ип
    0.08
    渴
    0.08
    ators
    0.08
    æİĢ
    0.08
    æĮ¹
    0.08
    ç¯ĵ
    0.08
    æ°¸éģł
    0.08
    Activations Density 0.434%

    No Known Activations