© 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. 16803
    Prev
    Next
    INDEX
    Explanations

    born in

    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
    ibel
    -0.11
    ä¸į让
    -0.10
     вообÑīе
    -0.09
    å®ł
    -0.09
    æ¯ıå¹´éĥ½
    -0.09
    erer
    -0.09
    AVE
    -0.08
    croft
    -0.08
    æ¯ıå¹´
    -0.08
    ä¸Ĭä¸ĸ纪
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸Ģ天
    0.10
    æļĹæļĹ
    0.09
    è¿Ļ件
    0.09
    注å®ļ
    0.09
    èµ·åºĬ
    0.09
    人们对
    0.09
    åľºåIJĪ
    0.09
     Verfügung
    0.08
    HY
    0.08
    ä¸ĢåĪĻ
    0.08
    Activations Density 0.127%

    No Known Activations