© 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. 49749
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and formulas

    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
    åĨįåĬł
    -0.07
     bÃło
    -0.06
    lij
    -0.06
    åĨįéĢļè¿ĩ
    -0.06
    ä¿ĿæĮģ稳å®ļ
    -0.06
    åĨįçĤ¹åĩ»
    -0.06
     Banc
    -0.06
     dwar
    -0.06
    æĻ®æ£®
    -0.06
    è¿Ľè¡Įå®£ä¼ł
    -0.06
    POSITIVE LOGITS
     outright
    0.08
    ooke
    0.07
    为ä¸Ń
    0.07
    缴æİ¥åľ¨
    0.07
    åĪĽ
    0.07
    iae
    0.07
    æĬĹåİĭ
    0.07
    abend
    0.07
    æĬĹ
    0.07
     ek
    0.07
    Activations Density 0.001%

    No Known Activations