© 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. 43242
    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
    iore
    -0.09
    æĸĩç«łæĿ¥æºIJ
    -0.08
     sted
    -0.08
    ä¸įåĢ¦
    -0.08
    ä¸Ńè¡Į
    -0.08
    ä¸įåİĮ
    -0.07
    ons
    -0.07
    uman
    -0.07
    ĵĺ
    -0.07
    æ¸ħ宫
    -0.07
    POSITIVE LOGITS
    cope
    0.08
    åĪĨåĪ«æĺ¯
    0.08
    äºķ
    0.07
    etus
    0.07
    对å¾ħ
    0.06
    ëį°
    0.06
    prite
    0.06
    aryl
    0.06
    :
    0.06
     Thứ
    0.06
    Activations Density 0.000%

    No Known Activations