© 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. 61845
    Prev
    Next
    INDEX
    Explanations

    Knight, ter, hot, os, adjusting, Minnesota, Ong, Adam, American, Discovery

    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
    ilo
    -0.07
    гови
    -0.07
    è°¤
    -0.07
    æ¯Ķæĸ¹
    -0.06
    urd
    -0.06
    ÃŃl
    -0.06
    _COMPILE
    -0.06
     {{{
    -0.06
    ＿＿
    -0.06
     Consulta
    -0.06
    POSITIVE LOGITS
    elow
    0.07
    icht
    0.07
    森çļĦ
    0.07
    æĺ¯ä¸Ģ大
    0.07
    ICLES
    0.07
    å·²åľ¨
    0.07
    ½Ķ
    0.07
    istos
    0.06
    strup
    0.06
    ä¸Ńå¿ĥåĴĮ
    0.06
    Activations Density 0.500%

    No Known Activations