© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63320
    Prev
    Next
    INDEX
    Explanations

    award winner

    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
     "".
    -0.08
    æĶ¶èĹıæľ¬ç«Ļ
    -0.07
    [sizeof
    -0.07
    éķIJ
    -0.07
     '".
    -0.07
    ä¸įè¨Ģ
    -0.07
     "'",
    -0.06
    pati
    -0.06
    åıĸåĨ³
    -0.06
    ç¤Ļ
    -0.06
    POSITIVE LOGITS
    ãģ¨ãģ¯ãģĦãģĪ
    0.07
     bowiem
    0.07
    ฯ
    0.07
    ãģĿãģĨãģª
    0.07
     ฯ
    0.06
    ëĵ±ìĿĦ
    0.06
    à¹īาย
    0.06
     vorgen
    0.06
    gger
    0.06
    rung
    0.06
    Activations Density 1.171%

    No Known Activations