© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48429
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    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
    èĢĮä¸įæĺ¯
    -0.08
    æīĢå±ŀåĪĨç±»
    -0.08
    utzer
    -0.07
    elum
    -0.07
    lut
    -0.07
    skr
    -0.07
    建ä¸ļ
    -0.06
    Straight
    -0.06
     зе
    -0.06
    agraph
    -0.06
    POSITIVE LOGITS
    agno
    0.09
    åı¯è¨Ģ
    0.08
     ника
    0.08
    عات
    0.08
    æĹłåħ³
    0.07
    å¸Ĥ人æ°ijæ³ķéĻ¢
    0.07
     żad
    0.07
    åĭī强
    0.07
     žádn
    0.07
     ни
    0.07
    Activations Density 0.216%

    No Known Activations