© 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. 63511
    Prev
    Next
    INDEX
    Explanations

    copying parts of text

    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
    art
    -0.07
     Maio
    -0.07
    oler
    -0.06
    èıģ
    -0.06
    -ish
    -0.06
    æĢªä¸įå¾Ĺ
    -0.06
    tav
    -0.06
    ÙĨت
    -0.06
    åĴĮæľ¬
    -0.06
    æŀĿ头
    -0.06
    POSITIVE LOGITS
    opedia
    0.08
    LOT
    0.08
    ocracy
    0.07
    amura
    0.07
    awang
    0.07
    ,:,:
    0.07
     dint
    0.07
    ä¹ĭçĶ¨
    0.07
    çĶ¨æ³ķ
    0.06
    è¸Ĭ
    0.06
    Activations Density 0.001%

    No Known Activations