© 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. 6085
    Prev
    Next
    INDEX
    Explanations

    permission for

    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
    åģľå·¥
    -0.10
    ç¼´
    -0.10
    å¥ī
    -0.10
    ç¡IJ
    -0.09
    æį¢ä¸ª
    -0.09
    è¯ł
    -0.08
    æ´ŀ
    -0.08
    移éĢģ
    -0.08
    DRAM
    -0.08
    绣é¢Ĩ
    -0.08
    POSITIVE LOGITS
    æĬĺåıł
    0.11
    满
    0.10
    å¹²éĥ¨
    0.09
    çĽĸ
    0.08
     Sage
    0.08
    é«ĺçŃī
    0.08
    umerator
    0.08
    忾
    0.08
    辨
    0.08
     Hoch
    0.08
    Activations Density 0.134%

    No Known Activations