© 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. 39924
    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
    onga
    -0.08
    åIJĬ
    -0.07
    åĤ¨
    -0.07
    onti
    -0.07
    绣
    -0.07
    .getComponent
    -0.06
     extrad
    -0.06
     Stem
    -0.06
    åĦ²
    -0.06
    ç¼Ŀ纫
    -0.06
    POSITIVE LOGITS
     lho
    0.07
    arz
    0.07
    èIJ¥åķĨçݯå¢ĥ
    0.07
    วà¸ĩ
    0.07
    Äĵr
    0.07
    å¤ĦçIJĨæĸ¹æ³ķ
    0.07
    æµ·å²Ľ
    0.07
    ä¸įå¾Ĺå·²
    0.07
    åĮĸå¤ĦçIJĨ
    0.07
    TTY
    0.07
    Activations Density 0.003%

    No Known Activations