© 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. 56711
    Prev
    Next
    INDEX
    Explanations

    NET Core MVC

    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
    dej
    -0.08
    vers
    -0.08
    ajari
    -0.08
    اج
    -0.08
    eraan
    -0.08
    å¾
    -0.07
    ãģĤãģ£
    -0.07
    æ£ĢæŁ¥å·¥ä½ľ
    -0.07
    Jvm
    -0.07
    quiry
    -0.07
    POSITIVE LOGITS
    antin
    0.07
     Forums
    0.07
    ling
    0.06
    -forward
    0.06
    å¤įæĹ¦å¤§åѦ
    0.06
    expo
    0.06
     prof
    0.06
     XMLHttpRequest
    0.06
    лам
    0.06
     exponent
    0.06
    Activations Density 0.007%

    No Known Activations