© 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. 7338
    Prev
    Next
    INDEX
    Explanations

    Prelims, DB9, cheerleader, Mango, Latin American, pseudodeficiency, GuiMacro, .ModelListener, messenger RNA, Practice Swimsuit

    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
    enis
    -0.08
    ä¸Ģå±Ĭ
    -0.07
    ock
    -0.07
    κοÏĤ
    -0.07
    è¡Įä¸ļèµĦ讯
    -0.07
    etin
    -0.07
    ooter
    -0.07
    ramework
    -0.06
    è¨Ī
    -0.06
    ocken
    -0.06
    POSITIVE LOGITS
     consign
    0.08
     getWindow
    0.07
    .firebaseapp
    0.07
    æī©å±ķèµĦæĸĻ
    0.07
     onDestroy
    0.06
    çīĪä¸ĭè½½
    0.06
    ören
    0.06
    Âł
    0.06
    dives
    0.06
    _Msk
    0.06
    Activations Density 0.152%

    No Known Activations