© 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. 30463
    Prev
    Next
    INDEX
    Explanations

    programming in various languages

    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
    iders
    -0.06
    ок
    -0.06
    笼
    -0.06
    itez
    -0.06
     statewide
    -0.06
     indisc
    -0.06
    èĥĮçĹĽ
    -0.06
    宣åŁİ
    -0.06
    Ta
    -0.06
    ders
    -0.06
    POSITIVE LOGITS
     parl
    0.07
    æĪij们ä¼ļ尽快
    0.07
    urv
    0.07
    ä¸Ń表示
    0.07
    antt
    0.07
    .NULL
    0.07
    __:
    0.07
    å·¥ç¨ĭéĻ¢éĻ¢å£«
    0.07
    _BLOCKS
    0.07
    oppi
    0.06
    Activations Density 0.118%

    No Known Activations