© 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. 47470
    Prev
    Next
    INDEX
    Explanations

    satisfactory or ideal outcome

    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
    stalk
    -0.09
    è¾İ
    -0.09
    åĩºåĬ¨
    -0.09
    è¿ĺ羣
    -0.08
    alker
    -0.08
    è·ŁçĿĢ
    -0.08
    ç»ĵåIJĪèµ·æĿ¥
    -0.08
    _logged
    -0.08
    AGED
    -0.08
    clin
    -0.08
    POSITIVE LOGITS
    满æĦıçļĦ
    0.26
    满æĦı
    0.22
     satisfactory
    0.18
    ä¸į满æĦı
    0.17
    å¾Ī满æĦı
    0.16
    满æĦı度
    0.15
     satisf
    0.14
    atisf
    0.13
     acceptable
    0.13
    à¸ŀà¸Ńà¹ĥà¸Ī
    0.12
    Activations Density 0.053%

    No Known Activations