© 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. 20156
    Prev
    Next
    INDEX
    Explanations

    chemical structures within parentheses

    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
    ostat
    -0.07
    é»İ
    -0.07
    essus
    -0.07
    andt
    -0.07
    åĩĨ
    -0.06
     situation
    -0.06
    åĵĦ
    -0.06
    еÑĤÑĮ
    -0.06
    çľ¼çľĭçĿĢ
    -0.06
    ì¡´
    -0.06
    POSITIVE LOGITS
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    0.09
    builder
    0.09
    udios
    0.08
    ENDO
    0.08
    代ä¼ļ
    0.07
    INY
    0.07
    æĤ¨å°Ĩ
    0.07
    ï¸İ
    0.07
    abase
    0.07
    åĩºå¸Ńä¼ļè®®
    0.07
    Activations Density 0.037%

    No Known Activations