© 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. 26362
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ÄĥrÄĥ
    -0.08
    å·®è·Ŀ
    -0.07
     ~=
    -0.07
    à¹Ģà¸ĭà¸Ńรà¹Į
    -0.07
    modifiable
    -0.07
     xÃŃch
    -0.07
    åıijçĤİ
    -0.07
    кÑĥÑĢÑģ
    -0.07
    åĴĮä¼ģä¸ļ
    -0.07
     Erg
    -0.07
    POSITIVE LOGITS
    å¦ĤåĽ¾æīĢ示
    0.07
    æĸ¥
    0.07
     ab
    0.07
    å¨Ĩ
    0.07
    é¹Ĭ
    0.07
    ä¸īä¸Ń
    0.07
    åģļé¢ĺ
    0.07
    æģ°
    0.06
    ab
    0.06
    ç«ĸ缴
    0.06
    Activations Density 0.000%

    No Known Activations