© 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. 43166
    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
    æ¸ħ
    -0.08
    ä¸įæķ£
    -0.06
    kä
    -0.06
    kler
    -0.06
    æ¸ħçļĦ
    -0.06
    ÛĮدÛĮ
    -0.06
    ÙĪعات
    -0.06
    ade
    -0.06
    ery
    -0.06
    æķĻ书
    -0.06
    POSITIVE LOGITS
    /cms
    0.09
    ajs
    0.09
    è¿Ľä¸ĢæŃ¥äºĨ解
    0.08
    æĿ¥åıĤåĬł
    0.08
    jun
    0.07
    (cps
    0.07
    à¦ŀà§įà¦ļ
    0.07
    -regexp
    0.07
    _PWR
    0.07
    cps
    0.07
    Activations Density 0.000%

    No Known Activations