© 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. 47527
    Prev
    Next
    INDEX
    Explanations

    itself, themselves, sich

    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
    绳
    -0.10
    èī®
    -0.09
    大家åı¯ä»¥
    -0.09
    è¾ŀ
    -0.09
    çļĦéĤ£ç§į
    -0.09
    å¢Ļä¸Ĭ
    -0.09
    æ¸Ń
    -0.09
     bast
    -0.08
    çļĦéĤ£ä¸ª
    -0.08
    åħ¨åŁŁ
    -0.08
    POSITIVE LOGITS
     itself
    0.15
    èĩªèº«çļĦ
    0.12
    èĩªèº«
    0.11
    æľ¬èº«
    0.11
    ÑıÑģÑĮ
    0.10
    èĩªåĬ¨
    0.10
     themselves
    0.10
    èµ·æĿ¥
    0.09
     sich
    0.09
     Automatically
    0.09
    Activations Density 0.048%

    No Known Activations