© 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. 63978
    Prev
    Next
    INDEX
    Explanations

    feel free to

    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
    azzi
    -0.09
    æļĹ
    -0.09
    麻çĹ¹
    -0.08
     Clover
    -0.08
     dòng
    -0.08
    ĸī
    -0.08
    æ¿ij
    -0.08
    ç¯Ļ
    -0.08
    ä¸ĢåıĮ
    -0.08
    .cz
    -0.08
    POSITIVE LOGITS
    ä¹IJæĦı
    0.13
    éļıæŶ
    0.11
     freely
    0.10
    æŃ¡è¿İ
    0.09
     willing
    0.09
    æĦ¿æĦı
    0.09
    éļ¨æĻĤ
    0.09
    欢è¿İ
    0.08
     welcome
    0.08
     SUBSTITUTE
    0.08
    Activations Density 0.045%

    No Known Activations