© 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. 12293
    Prev
    Next
    INDEX
    Explanations

    negatives events and crises

    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
    娶
    -0.10
    çķĮ第ä¸Ģ
    -0.09
    æĺ¯ä¸įåı¯èĥ½
    -0.09
    åĴĴ
    -0.09
    å§ĭ建
    -0.09
    å¾ħ
    -0.09
    è§ħ
    -0.09
     concess
    -0.09
    -Mar
    -0.08
    æĶ¾æīĭ
    -0.08
    POSITIVE LOGITS
    æ¡Īä¾ĭ
    0.12
    æĤ²åī§
    0.11
    åľ¨è¿Ļæĸ¹éĿ¢
    0.10
    æķĻè®Ń
    0.10
    ä¾ĭåŃIJ
    0.10
    大éĿ¢ç§¯
    0.10
    éĢĿ
    0.09
    个åĪ«
    0.09
     Roller
    0.09
    浪费
    0.09
    Activations Density 0.112%

    No Known Activations