© 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. 16079
    Prev
    Next
    INDEX
    Explanations

    numbers and time

    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
    çļĦ
    -0.07
    æĢª
    -0.06
     Yin
    -0.06
    ä½Ĩæĺ¯å¯¹äºİ
    -0.06
    对äºİ
    -0.06
    è¾ľ
    -0.06
    ä¸İä¼Ĺ
    -0.06
    对äºİè¿Ļ个
    -0.06
    .instrument
    -0.06
    em
    -0.06
    POSITIVE LOGITS
    arella
    0.08
    åľ¨åŃ¦ä¹łä¸Ń
    0.08
    bulk
    0.07
    ä¸ĢåĪĻ
    0.07
    å±ħä½ıåľ¨
    0.07
    ihat
    0.07
    西æĸ¯
    0.07
    osh
    0.07
    ä¸Ģé«Ķ
    0.07
    irting
    0.07
    Activations Density 0.107%

    No Known Activations