© 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. 24118
    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
     ÙĨÙģسÙĩ
    -0.07
    åĪĪ
    -0.07
     itself
    -0.07
    ?>>
    -0.07
    elsif
    -0.07
    紧迫
    -0.07
    æĸĩèīºæ¼Ķåĩº
    -0.07
     Norwich
    -0.07
    çļĦä¸Ģ声
    -0.06
    azine
    -0.06
    POSITIVE LOGITS
     سرا
    0.07
    inth
    0.07
    OME
    0.07
    InThe
    0.07
    orida
    0.07
    éĿłçĿĢ
    0.07
     omas
    0.06
    RIA
    0.06
     âĸ¼
    0.06
    寰
    0.06
    Activations Density 0.781%

    No Known Activations

    This feature has no known activations.