© 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. 7791
    Prev
    Next
    INDEX
    Explanations

    warm greetings and physical sensations

    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
    æİī
    -0.11
    æİīäºĨ
    -0.11
    æıIJæĮ¯
    -0.09
    idis
    -0.09
     pac
    -0.09
    éĽĨä¸Ńåľ¨
    -0.09
    åѱ
    -0.08
    azzi
    -0.08
    æĻļä¸Ĭ
    -0.08
    æİīèIJ½
    -0.08
    POSITIVE LOGITS
    uler
    0.10
    æĦŁäºº
    0.09
    åIJĦçķĮ
    0.09
    icals
    0.08
    æĦŁæĥħ
    0.08
    /gpl
    0.08
    ULER
    0.08
    æľ¨åľ°æĿ¿
    0.08
    füh
    0.08
    bsd
    0.08
    Activations Density 0.004%

    No Known Activations