© 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. 63762
    Prev
    Next
    INDEX
    Explanations

    business options

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åįķåħĥ
    -0.09
    ModelError
    -0.08
    çķ¹
    -0.08
    è¦ģæľī
    -0.08
     Lange
    -0.08
    _compiler
    -0.07
    pered
    -0.07
    äºĭä¸ļåįķä½į
    -0.07
    责任人
    -0.07
    reas
    -0.07
    POSITIVE LOGITS
    éĢįéģ¥
    0.11
    æİ¥åħ¥
    0.10
    为客æĪ·
    0.10
    æľįåĬ¡è´¨éĩı
    0.10
    ä¸İä¼Ĺä¸įåIJĮ
    0.10
    æľįåĬ¡åķĨ
    0.09
    ä¸ļåĨħ
    0.09
    åĬłçĽŁ
    0.09
    为æĤ¨æıIJä¾Ľ
    0.09
    ä¸ļæĢģ
    0.09
    Activations Density 0.269%

    No Known Activations