© 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. 63373
    Prev
    Next
    INDEX
    Explanations

    decoy, tango, anabolic, Mercury, marriage

    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
    å¼ĥçĸ¾
    -0.08
    éħİ
    -0.07
    ä»»æĢ¨
    -0.07
    æŃ¤èµ·å½¼
    -0.07
    åĽ¾ä¸ŃäºĮç»´çłģ
    -0.07
    ãĤ«ãĤ¸
    -0.07
    纳士
    -0.07
    aleb
    -0.07
    åıij表讨论
    -0.07
    çīĪæĿĥå±ŀäºİ
    -0.07
    POSITIVE LOGITS
     
    0.07
    
    0.06
    âĢİ
    0.06
    âĢIJ
    0.06
    æĢĿæĥ³åĴĮè¡ĮåĬ¨
    0.06
    ÑĪки
    0.06
     âĢķ
    0.06
    .initialize
    0.06
    mark
    0.06
    ï¼İ
    0.06
    Activations Density 0.333%

    No Known Activations