© 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. 14361
    Prev
    Next
    INDEX
    Explanations

    corresponding (word/phrase)

    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
    er
    -0.08
    erio
    -0.07
    çļĦå°±æĺ¯
    -0.07
    è¿Ļæł·ä¸Ģ个
    -0.07
    erot
    -0.06
    λεί
    -0.06
    opedia
    -0.06
    atlan
    -0.06
    erat
    -0.06
    okrat
    -0.06
    POSITIVE LOGITS
    æĶ¾çŁ¢
    0.09
    iating
    0.09
     respective
    0.09
    缸åºĶçļĦ
    0.08
    ingly
    0.08
    èĢĮæĿ¥çļĦ
    0.08
    ä¸ļåĬ¡æ°´å¹³
    0.08
    ież
    0.08
    ستا
    0.08
    ropriate
    0.08
    Activations Density 0.058%

    No Known Activations