© 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. 28985
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and symbols

    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
    ä¸Ģ空
    -0.07
    è§Ī
    -0.07
    acob
    -0.07
     Loved
    -0.07
    BAN
    -0.07
    ÃŃba
    -0.06
    licht
    -0.06
     зал
    -0.06
    åIJ§
    -0.06
    å·´å·´
    -0.06
    POSITIVE LOGITS
    çļĦåĶ¯ä¸Ģ
    0.07
    ä¼ģä¸ļç®Ģä»ĭ
    0.07
    å¾µ
    0.07
    argout
    0.07
    ä¸įæĺĵ
    0.07
    ä¸įèĢIJ
    0.07
    ensi
    0.06
    ç»Ŀ对ä¸įæĺ¯
    0.06
    ä¸į容æĺĵ
    0.06
    æĺ¯ä¸įå¤Ł
    0.06
    Activations Density 0.003%

    No Known Activations