© 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. 41190
    Prev
    Next
    INDEX
    Explanations

    potential disorder interaction

    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
    ptime
    -0.08
    enaus
    -0.07
    ruz
    -0.07
    èĬ³åįİ
    -0.07
     Toil
    -0.06
    代人
    -0.06
    ä¹ĭåħī
    -0.06
    é²ľèĤī
    -0.06
    建åĨĽ
    -0.06
    ä¸įåIJĮæĦı
    -0.06
    POSITIVE LOGITS
    åĬ¿
    0.08
     Lange
    0.08
    ype
    0.08
    åºĵ
    0.08
    _logits
    0.07
    antis
    0.07
    æĭīéĩĮ
    0.07
    诱æĥij
    0.07
    å¾ĦåIJij
    0.07
    åIJ¸å¼ķ
    0.07
    Activations Density 0.016%

    No Known Activations