© 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. 64074
    Prev
    Next
    INDEX
    Explanations

    social media commenting and complaints

    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
    ä¸İæŶ
    -0.11
     اÙĦÙħصدر
    -0.10
     моÑīн
    -0.10
    ä¾Ľå¤§å®¶
    -0.10
     Fiat
    -0.10
    oref
    -0.10
    æĻļå¹´
    -0.10
    ä»İæĿ¥æ²¡
    -0.10
    é£İåIJ¹
    -0.09
    ä½Ĩæĺ¯ä»ĸ
    -0.09
    POSITIVE LOGITS
    纷纷
    0.10
    æľīçļĦ
    0.09
    纷纷表示
    0.09
    è¿Ļä¸Ģ天
    0.09
     @
    0.08
    ä¸Ģèĩ´
    0.08
    ä¸Ģå¤ľ
    0.08
    è¸
    0.08
     cul
    0.08
    è¸Ĭè·ĥ
    0.08
    Activations Density 0.192%

    No Known Activations