© 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. 12287
    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
    Ø·
    -0.07
    orsa
    -0.06
    wyn
    -0.06
     commanding
    -0.06
    itled
    -0.06
    inces
    -0.06
    æĿ¥æºIJç½ij绾
    -0.06
    ptico
    -0.06
    ourd
    -0.06
    å¹¢
    -0.06
    POSITIVE LOGITS
    agai
    0.08
    SSIP
    0.08
    éľĦ
    0.08
     Guys
    0.08
     ÎŃν
    0.08
    mén
    0.07
    gua
    0.07
    ackle
    0.07
    åIJĮ声
    0.07
    زÙĪÙĨ
    0.07
    Activations Density 0.000%

    No Known Activations