© 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. 40030
    Prev
    Next
    INDEX
    Explanations

    new to programming frameworks

    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
    pects
    -0.07
    Aj
    -0.07
    ãģ¿ãģŁ
    -0.06
    ä¸ĬæĿ¥çļĦ
    -0.06
    ä¸Ĭæ·»
    -0.06
    åĴĮéĩįçĤ¹
    -0.06
    ÙİعÙĴ
    -0.06
    NQ
    -0.06
    pflicht
    -0.06
    ÙĪÛĮÛĮ
    -0.06
    POSITIVE LOGITS
     terminology
    0.09
    ahanan
    0.08
    raph
    0.07
    μαÏĦο
    0.07
    озна
    0.07
    çIJĨè®ºçŁ¥è¯Ĩ
    0.07
    åıijå±ķåİĨç¨ĭ
    0.07
     CHARSET
    0.07
    /php
    0.07
    ]-$
    0.07
    Activations Density 0.060%

    No Known Activations