© 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. 12339
    Prev
    Next
    INDEX
    Explanations

    people's attributes or states

    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
    å®ĥçļĦ
    -0.11
    è¿Ļåıª
    -0.09
    æĺ¯ä¸Ģä½į
    -0.09
    èļ¤
    -0.09
    æµ·æ£ł
    -0.09
    éĤ£ä½ł
    -0.09
     Holidays
    -0.09
    éĤ£åıª
    -0.09
    è¿Ļå¼ł
    -0.08
     its
    -0.08
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.22
    åIJĦèĩª
    0.21
    她们
    0.16
     themselves
    0.14
     Ñģами
    0.14
    家éķ¿ä»¬
    0.13
     respective
    0.13
    ä»ĸ们
    0.13
    ä»ĸ们çļĦ
    0.13
    ä½Ĩä»ĸ们
    0.12
    Activations Density 0.333%

    No Known Activations