© 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. 27848
    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
    并ä¸į代表
    -0.07
    ukai
    -0.07
    tick
    -0.06
    æĮĩçļĦæĺ¯
    -0.06
    çļĦä¸Ģå®ļ
    -0.06
    alo
    -0.06
     strictly
    -0.06
    ç½Ĺåħ°
    -0.06
    çIJħ
    -0.06
    èİİæĭī
    -0.06
    POSITIVE LOGITS
    zis
    0.09
    ä¾µçĬ¯æĤ¨çļĦ
    0.08
    enga
    0.07
     trái
    0.07
    igus
    0.07
    .Op
    0.07
    _aug
    0.07
    epass
    0.07
    halten
    0.07
    èıģ
    0.07
    Activations Density 0.000%

    No Known Activations