© 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. 19315
    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
    othing
    -0.07
    GLOSS
    -0.07
    èĩ¼
    -0.07
     Vạn
    -0.07
    å°ĨæĿ¥
    -0.07
    plo
    -0.07
     Ranh
    -0.07
    kaar
    -0.07
    西åħ°
    -0.07
    ×ķ×Ļ
    -0.07
    POSITIVE LOGITS
    _printer
    0.07
    éĢ¢
    0.07
    wright
    0.07
    符
    0.07
    äºĮåįĥ
    0.06
    è¾Ľéħ¸
    0.06
     Dang
    0.06
     discharged
    0.06
    è¿Ļä¸Ģå¹ķ
    0.06
    cad
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.