© 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. 23426
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    被å¥Ĺ
    -0.08
    ately
    -0.08
    åIJĮ声
    -0.07
     basics
    -0.07
    hluk
    -0.07
    ëķĮ
    -0.07
    éĻĽ
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.07
    éĩij鸡
    -0.06
    onos
    -0.06
    POSITIVE LOGITS
     Info
    0.07
    ä¸ŃçļĦæķ°æį®
    0.07
    quist
    0.07
    éĨ
    0.07
    umann
    0.07
    æĢ¥
    0.07
    ä½
    0.07
    Info
    0.06
    èĪ
    0.06
    stes
    0.06
    Activations Density 0.000%

    No Known Activations