© 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. 60639
    Prev
    Next
    INDEX
    Explanations

    theme or thematic analysis

    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
    åħħåĪĨ
    -0.10
    ogie
    -0.09
     reflex
    -0.08
    ä¸Ģåı£
    -0.08
    æİĮæı¡
    -0.08
    칸
    -0.08
    adians
    -0.08
    å¥ł
    -0.08
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.08
    iid
    -0.08
    POSITIVE LOGITS
    主é¢ĺ
    0.30
    çļĦ主é¢ĺ
    0.28
     themes
    0.27
     theme
    0.26
    theme
    0.24
    为主é¢ĺ
    0.24
    Theme
    0.22
    ãĥĨãĥ¼ãĥŀ
    0.22
    主é¡Į
    0.22
    _theme
    0.21
    Activations Density 0.079%

    No Known Activations