© 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. 23054
    Prev
    Next
    INDEX
    Explanations

    between subscribers and servers

    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
     Herz
    -0.07
    天ä¸ĭ第ä¸Ģ
    -0.07
    eres
    -0.07
    åIJijèį£
    -0.06
    éļľ
    -0.06
    OnInit
    -0.06
    .tp
    -0.06
    ä¸ĭ表
    -0.06
    ä¸Ģå¿ĥ
    -0.06
    æĿ¿åĩ³
    -0.06
    POSITIVE LOGITS
    Įĵ
    0.08
    aldi
    0.08
    mts
    0.07
    缴æİ¥ä¸İ
    0.07
    åı¯ä»¥çĽ´æİ¥
    0.07
     exchanging
    0.07
     intermediate
    0.07
    éħ¬
    0.07
    缴æݥ被
    0.07
     exchanges
    0.07
    Activations Density 0.039%

    No Known Activations