© 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. 2194
    Prev
    Next
    INDEX
    Explanations

    operating methods and techniques

    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
    ä¸įåı¯æĢķ
    -0.07
    оÑģÑĤо
    -0.07
    intree
    -0.07
    اÙħت
    -0.07
    oba
    -0.07
     Verse
    -0.07
    Allocator
    -0.07
    _Impl
    -0.07
    ltk
    -0.07
    LOCKS
    -0.06
    POSITIVE LOGITS
     Canyon
    0.07
    æīĭæ³ķ
    0.07
    åĬŁ
    0.07
     factors
    0.07
    éħįåIJĪ
    0.07
    端çĿĢ
    0.07
    ä¸įå½ĵ
    0.07
    西åŁİ
    0.07
    æīĵæ³ķ
    0.07
    åĽłç´ł
    0.07
    Activations Density 0.219%

    No Known Activations