© 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. 24174
    Prev
    Next
    INDEX
    Explanations

    unacceptable or wrong judgment

    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
    arme
    -0.09
    éĦ¢
    -0.09
    çļĦåŁºç¡Ģ
    -0.09
    æĶ¯æŁ±
    -0.09
    éĹ´æİ¥
    -0.08
     thiá»ĩn
    -0.08
    åıįæŃ£
    -0.08
    å¹²èĦĨ
    -0.08
    .gradle
    -0.08
    æ¦Ħ
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ı
    0.15
    ä»»ä½ķ
    0.14
    æĹłè®ºæĺ¯
    0.13
    æĹłè®º
    0.13
    è¡Į为
    0.13
     unacceptable
    0.13
    ä¸į论
    0.12
    ä¸į管æĺ¯
    0.12
    çĦ¡è«ĸ
    0.11
    ä»»ä½ķæŶåĢĻ
    0.11
    Activations Density 0.045%

    No Known Activations