© 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. 47613
    Prev
    Next
    INDEX
    Explanations

    ID or identification

    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
    æIJĵ
    -0.10
    æĭįæĭį
    -0.10
    ä¸ĢæīĢ
    -0.09
    æ¡´
    -0.09
    笮
    -0.09
    çĶļ
    -0.09
    åIJ¬è¯´
    -0.09
    สà¸Ļ
    -0.09
    人éĢī
    -0.09
    èįª
    -0.08
    POSITIVE LOGITS
    å²Ĺ
    0.10
     badge
    0.10
    佩æĪ´
    0.10
    desk
    0.09
    è¯ģ件
    0.09
    两æĿ¡
    0.09
    æ¹ĸåĮº
    0.09
    å·¥ä½ľç«Ļ
    0.09
    æŀķ
    0.09
    èĤ¡
    0.09
    Activations Density 0.050%

    No Known Activations