© 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. 28387
    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
    iesen
    -0.07
     Brock
    -0.06
    å·¥ä½ľå®īæİĴ
    -0.06
    è´¨
    -0.06
    ssp
    -0.06
    åįĹçľģ
    -0.06
    ulo
    -0.06
    elaar
    -0.06
    _timing
    -0.06
    éĹ´è·Ŀ
    -0.06
    POSITIVE LOGITS
    æĬĬèĩªå·±çļĦ
    0.08
    æĬĬä½łçļĦ
    0.08
    ç«£
    0.08
    æĹĭ
    0.08
    æľ¬åĬŀæ³ķ
    0.07
    ØŃÙĬÙĨ
    0.07
    æĬĬè¿ĻäºĽ
    0.07
    uez
    0.07
     adren
    0.07
    uhn
    0.07
    Activations Density 0.000%

    No Known Activations