© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59092
    Prev
    Next
    INDEX
    Explanations

    publisher names and institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    eku
    -0.08
    æģ¯çļĦ
    -0.08
    æĹıèĩªæ²»åİ¿
    -0.07
    ä½ıéĻ¢æ²»çĸĹ
    -0.07
     rud
    -0.07
    entro
    -0.07
    ẩn
    -0.07
    åĽ¢
    -0.07
    éĽ·è¯º
    -0.07
    ovement
    -0.07
    POSITIVE LOGITS
    ä¸įèĭŁ
    0.08
     Ñĥк
    0.07
    åı¯èĥ½å°±æĺ¯
    0.07
    ä¼ĺç§Ģ
    0.06
     Publishers
    0.06
    OrCreate
    0.06
    crest
    0.06
    åįģ
    0.06
     Verlag
    0.06
    -B
    0.06
    Activations Density 0.025%

    No Known Activations