© 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. 18591
    Prev
    Next
    INDEX
    Explanations

    diagnosis and classification codes

    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
    æĮĻ
    -0.07
    éĢ¼
    -0.07
     воÑģ
    -0.06
    æijĨ
    -0.06
     quen
    -0.06
    ÙĦاع
    -0.06
    设æ³ķ
    -0.06
     dubbed
    -0.06
    å·¥ä¸ļ设计
    -0.06
     qu
    -0.06
    POSITIVE LOGITS
    大类
    0.10
    -category
    0.10
    ç¼ĸçłģ
    0.09
    หมวà¸Ķ
    0.09
     categories
    0.09
    Codes
    0.09
     category
    0.09
     codes
    0.09
    åĪĨç±»
    0.09
    å½Ĵç±»
    0.09
    Activations Density 0.053%

    No Known Activations