© 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. 41185
    Prev
    Next
    INDEX
    Explanations

    code and markup delimiters

    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
    sko
    -0.08
    çĽ¸å¯¹èĢĮè¨Ģ
    -0.07
     dalje
    -0.07
    æĬĵç´§
    -0.07
    鼻窦
    -0.07
    azz
    -0.07
    åIJĮæł·æĺ¯
    -0.07
    å¦ĤæѤä¸ĢæĿ¥
    -0.07
    /locale
    -0.06
    ìŀ¡
    -0.06
    POSITIVE LOGITS
    çĮİ
    0.06
    åIJijå¾Ģ
    0.06
     elas
    0.06
    ï¸İ
    0.06
    pira
    0.06
    åªĴ
    0.06
    orten
    0.06
    çįµ
    0.06
    çĮİ人
    0.06
    ampia
    0.06
    Activations Density 0.004%

    No Known Activations