© 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. 56463
    Prev
    Next
    INDEX
    Explanations

    ctype.h include

    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
    纳德
    -0.09
    ФÐŀ
    -0.08
    .func
    -0.08
    nette
    -0.07
    çļĦå°ıä¼Ļ
    -0.07
    尼奥
    -0.07
    Ļ
    -0.07
    ä¾ĽåĽ¾
    -0.07
    满èħĶ
    -0.07
    å¤©æ±ł
    -0.07
    POSITIVE LOGITS
    åħīè¾ī
    0.07
    éĢ¼
    0.06
    hack
    0.06
    åħ«ä¹Ŀ
    0.06
    isdigit
    0.06
    8
    0.06
    žia
    0.06
    OTES
    0.06
    ä¹Ķæ²»
    0.06
    оÑĤов
    0.06
    Activations Density 0.006%

    No Known Activations