© 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. 50213
    Prev
    Next
    INDEX
    Explanations

    Zhou dynasty

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    opedia
    -0.10
    å¾ĭ師
    -0.09
    ä¿IJ
    -0.09
    婪
    -0.09
    ewire
    -0.09
    ä½ĵåĨħçļĦ
    -0.09
    monton
    -0.09
    è´ħ
    -0.09
    éŃĶå¹»
    -0.09
    æĥ³æĸ¹
    -0.09
    POSITIVE LOGITS
    åŃĶåŃIJ
    0.13
    åĦĴ家
    0.11
    åIJĽåŃIJ
    0.09
    å¼ŁåŃIJ
    0.09
    诸侯
    0.09
    以德
    0.09
    åŃIJæĽ°
    0.08
    论è¯Ń
    0.08
    æĺ¥ç§ĭ
    0.08
    åħ¬åŃĻ
    0.08
    Activations Density 0.001%

    No Known Activations