© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15834
    Prev
    Next
    INDEX
    Explanations

    equal or greater than

    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
    ×ľ×ª
    -0.08
    ä¸¥æł¼è¦ģæ±Ĥèĩªå·±
    -0.08
    ÑĨов
    -0.08
    IMITIVE
    -0.08
    ifax
    -0.07
     demonstrators
    -0.07
    alborg
    -0.07
    tul
    -0.07
    NU
    -0.07
    åħ±åĴĮåħļ
    -0.07
    POSITIVE LOGITS
     formula
    0.07
    Formula
    0.07
    å¤ĸæİ¥
    0.07
    åħ¬å¼ı
    0.07
    ĸ
    0.07
    å±±é«ĺ
    0.07
     tang
    0.07
    ä¸Ń线
    0.07
     equ
    0.07
     Rela
    0.07
    Activations Density 0.002%

    No Known Activations