© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14776
    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
    å¤ļ空
    -0.08
    leter
    -0.07
    éĥ¨éĥ¨éķ¿
    -0.07
    两头
    -0.07
     Pool
    -0.07
    umer
    -0.07
    èĽĽ
    -0.07
    idler
    -0.07
    Ģ
    -0.07
    epend
    -0.07
    POSITIVE LOGITS
     circumference
    0.08
    witz
    0.07
    estre
    0.07
    ãĥijãĤ¹
    0.07
    ogh
    0.07
     isol
    0.07
    æ¼Ĩ
    0.07
    天çİĭ
    0.07
    plik
    0.07
    å¤įåħ´
    0.07
    Activations Density 0.005%

    No Known Activations