© 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. 51430
    Prev
    Next
    INDEX
    Explanations

    Japanese patent or actor

    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
    对ä¸Ĭè¿°
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.06
    æĺ¯ä¸įå¤Ł
    -0.06
    etz
    -0.06
    inate
    -0.06
    è¿Ŀåıįä¸Ĭè¿°
    -0.06
    deal
    -0.06
    yasi
    -0.06
    kte
    -0.06
    (/^\
    -0.06
    POSITIVE LOGITS
    åıĪåIJį
    0.08
    çŃīçŃī
    0.08
    à¸Ńà¸Ļ
    0.07
    aney
    0.07
    âĢ¦)
    0.07
     âĢ¦
    0.07
     .....
    0.07
    aneo
    0.07
    &S
    0.07
    çŃīåIJĦç§į
    0.07
    Activations Density 0.076%

    No Known Activations