© 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. 65261
    Prev
    Next
    INDEX
    Explanations

    data structure or query context

    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
    åIJķ
    -0.07
    inker
    -0.06
    áy
    -0.06
    usel
    -0.06
    ayers
    -0.06
    çĭ¬è¡Į
    -0.06
    è·¯ä¸ľ
    -0.06
    æĿ°
    -0.06
    éŵ
    -0.06
    西路
    -0.06
    POSITIVE LOGITS
    åľ¨ä¸Ĭè¿°
    0.08
    hini
    0.07
    éĢļè¿ĩ以ä¸Ĭ
    0.07
    è´¨éĩıå®īåħ¨
    0.07
    зиÑĢа
    0.07
    udin
    0.07
    ypo
    0.07
    åıĤéĺħ
    0.07
    _PARAMETERS
    0.07
    æĸĩæijĺ
    0.07
    Activations Density 0.017%

    No Known Activations