© 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. 64034
    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
     atop
    -0.08
    _deps
    -0.07
    tingham
    -0.07
     val
    -0.07
    Ñģед
    -0.07
    åı¯ä¾Ŀ
    -0.06
    åįģä¸Ģ
    -0.06
    utang
    -0.06
    çĨĦ
    -0.06
    éĩįçĤ¹ä¼ģä¸ļ
    -0.06
    POSITIVE LOGITS
    errors
    0.07
    .keyword
    0.07
    æ°Ľ
    0.07
    符
    0.07
    assistant
    0.07
    itra
    0.06
    earn
    0.06
    irti
    0.06
    æĦıå¤ĸçļĦ
    0.06
    æĺ¥æĿ¥
    0.06
    Activations Density 0.000%

    No Known Activations