© 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. 50940
    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
    ixe
    -0.07
    被ä»ĸ
    -0.07
    æĬĢæľ¯çļĦåıijå±ķ
    -0.07
    ä¸ĩçī©
    -0.07
    åİ»åIJ§
    -0.06
    ievi
    -0.06
    å°ģç¥ŀ
    -0.06
     '\'
    -0.06
    iders
    -0.06
    สิà¸ģ
    -0.06
    POSITIVE LOGITS
    uille
    0.08
    èĩªå¾Ĺ
    0.08
    chel
    0.07
    åIJijæĿ¥
    0.07
    _SOL
    0.07
    åį¡åľ¨
    0.07
    riend
    0.07
     заклÑİÑĩа
    0.07
    ä¸ĢåIJij
    0.07
     pertanto
    0.07
    Activations Density 0.001%

    No Known Activations