© 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. 26572
    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
    axed
    -0.08
    æīİæīİå®ŀ
    -0.08
    terek
    -0.08
    ULLET
    -0.07
    isodes
    -0.07
    screen
    -0.07
    è´£ç¼ĸ
    -0.07
    å¾Ĺ天
    -0.07
    åįģåħ¨
    -0.07
    ç§įç§įåİŁåĽł
    -0.07
    POSITIVE LOGITS
    alu
    0.08
    åİĨåı²ä¸Ĭ
    0.07
    gon
    0.07
     Mau
    0.07
    hre
    0.06
    _executor
    0.06
    åıĺæį¢
    0.06
    æŃ´
    0.06
    py
    0.06
    öz
    0.06
    Activations Density 0.000%

    No Known Activations