© 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. 19156
    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
    åįģåĽĽç«ł
    -0.08
    ioc
    -0.07
     trÆ°á»Łng
    -0.07
    åįģåħ«ç«ł
    -0.07
    èĢĮçŁ¥
    -0.06
    è½®åĽŀ
    -0.06
    æľīä¸ĢäºĽ
    -0.06
    oki
    -0.06
    èĢĮåIJĮ
    -0.06
    vers
    -0.06
    POSITIVE LOGITS
    /ubuntu
    0.07
    ulp
    0.07
    IDL
    0.07
    Õ¡Öģ
    0.07
    å°ijä¸įäºĨ
    0.07
    itev
    0.07
    defer
    0.06
    bins
    0.06
    æŀľåĨ»
    0.06
    _REAL
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.