© 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. 22868
    Prev
    Next
    INDEX
    Explanations

    Jeremy Campbell, Kyle Jones, Emma Stevenson

    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
    æĹĭåį³
    -0.07
    æİĴåįµ
    -0.07
    榻
    -0.07
     tê
    -0.07
     uintptr
    -0.07
    jong
    -0.07
    lipp
    -0.07
    ä¸įæĥ§
    -0.06
    Trader
    -0.06
    天åŃIJ
    -0.06
    POSITIVE LOGITS
    eschi
    0.07
    为æĤ¨æݨèįIJ
    0.07
    åĸµåĸµ
    0.07
    arczy
    0.07
    enje
    0.07
    åħ¼æĢ»ç»ıçIJĨ
    0.06
    VML
    0.06
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.06
    /******/
    0.06
    ç¨ĭ度çļĦ
    0.06
    Activations Density 1.126%

    No Known Activations