© 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. 26173
    Prev
    Next
    INDEX
    Explanations

    change or alter

    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
    æĹłæīĢ
    -0.10
    èµ·æĿ¥
    -0.09
    空åīį
    -0.09
    ç©¿ä¸Ĭ
    -0.09
    è¥Ħ
    -0.09
    åIJĮç±»
    -0.09
    æĺ¯çľŁçļĦ
    -0.09
    éĻIJ
    -0.08
    ä¸įåĨį
    -0.08
     diss
    -0.08
    POSITIVE LOGITS
    åİŁæľīçļĦ
    0.12
    太å¤ļçļĦ
    0.12
    ä¸Ŀ毫
    0.11
    çİ°æľīçļĦ
    0.11
    太å¤ļ
    0.11
    æľīä»»ä½ķ
    0.11
    è¿ĩå¤ļ
    0.10
    dÃŃ
    0.10
    ä¿ĿæĮģçĿĢ
    0.10
    ä¹Łä¸įä¼ļ
    0.10
    Activations Density 0.079%

    No Known Activations