© 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. 42330
    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
    è¿ĻæŃ£æĺ¯
    -0.07
    RG
    -0.07
    éĢļçĶ¨çļĦ
    -0.07
    åĬĽéĩıçļĦ
    -0.07
    less
    -0.06
    è¿Ļ便æĺ¯
    -0.06
    æĬĬäºĭæĥħ
    -0.06
    æł¹æį®åħ¬åı¸
    -0.06
    ä»¥æĽ´
    -0.06
    ç«Ļç«Ļ
    -0.06
    POSITIVE LOGITS
    çµ®
    0.08
    itar
    0.08
    OnChange
    0.07
    AZE
    0.07
    å¤§åľ£
    0.07
    éĩĮéĿ¢çļĦ
    0.07
    ä½ĵç³»ä¸Ń
    0.07
    agar
    0.07
    æĢ§è´¨
    0.07
    è¯ķ管
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.