© 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. 60089
    Prev
    Next
    INDEX
    Explanations

    cross-lingual answers

    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
    Not in Any Lists

    No Comments

    Negative Logits
    _ASCII
    -0.06
    æĭ¼
    -0.06
    ún
    -0.06
    åĩ¤
    -0.06
    èµĭ
    -0.06
    ugh
    -0.06
    缴
    -0.06
    ainless
    -0.06
    è¿Ļ个è¯į
    -0.06
    äh
    -0.06
    POSITIVE LOGITS
    è¿ĻäºĽéĥ½æĺ¯
    0.08
     respectively
    0.08
    让åijĺå·¥
    0.08
    ãģĿãĤĮãģŀãĤĮ
    0.08
     모ëijIJ
    0.08
    .nd
    0.08
     serta
    0.08
    éĥ½æĺ¯æĪij
    0.08
    ãģ¨ãĤĤãģ«
    0.07
    åħ±ãģ«
    0.07
    Activations Density 0.173%

    No Known Activations