© 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. 1276
    Prev
    Next
    INDEX
    Explanations

    Asia, gold, lung, China, Foundation

    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
    å¹´è¿Ī
    -0.06
    ÙħÙĬÙħ
    -0.05
    å°ıæ¡¥
    -0.05
    ("--------------------------------
    -0.05
    å°¿å¸ĥ
    -0.05
     lá»ģ
    -0.05
    åİļå¾·
    -0.05
    èĢģå¦Ī
    -0.04
    ÙħÛĮÙħ
    -0.04
    .isAdmin
    -0.04
    POSITIVE LOGITS
    mousemove
    0.08
    .ascii
    0.07
    ElementsByTagName
    0.07
    /slick
    0.07
    DialogTitle
    0.07
     EntryPoint
    0.07
    aner
    0.06
     véhic
    0.06
    çŃīåĽ½éĻħ
    0.06
    ìģ
    0.06
    Activations Density 9.103%

    No Known Activations