© 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. 39513
    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
    one
    -0.07
    COPY
    -0.06
     Silva
    -0.06
    -0.06
    ä¼łéĢĴ
    -0.06
    ège
    -0.06
     Chau
    -0.05
    -0.05
    俯åį§
    -0.05
    vell
    -0.05
    POSITIVE LOGITS
    缸åħ³ä¸ļåĬ¡
    0.08
    姫
    0.08
    Ïģιά
    0.08
    .NET
    0.08
    coder
    0.08
     Ñģвободно
    0.08
     Barcellona
    0.08
    éĿĴæ¢ħ
    0.08
    ixin
    0.08
     Loader
    0.08
    Activations Density 0.000%

    No Known Activations