© 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. 34480
    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
    çŁ¥è¯Ĩ产æĿĥå±Ģ
    -0.08
    ä¸ŀ
    -0.07
    agine
    -0.07
    _PO
    -0.07
    letcher
    -0.07
    __[
    -0.07
    åĮ»éĻ¢è¿Ľè¡Į
    -0.07
    大éĥ¨ä»½
    -0.07
    zcz
    -0.07
    inbox
    -0.07
    POSITIVE LOGITS
    åīį款
    0.10
    第äºĮ款
    0.07
    第ä¸Ģ款
    0.07
    æľīä¸ĭåĪĹ
    0.07
    ä¸įå¾Ĺ
    0.06
    æľīæѤ
    0.06
    ä¸įå¾Ĺ以任ä½ķ
    0.06
    ä¸Ĭè¿°
    0.06
    é¡»ç»ı
    0.06
    æ¯Ķçħ§
    0.06
    Activations Density 0.000%

    No Known Activations