© 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. 18527
    Prev
    Next
    INDEX
    Explanations

    priceless reaction, shows limitations, riot funny

    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
    èĩªå·±çļĦèĥ½åĬĽ
    -0.08
    好ä¸ĢçĤ¹
    -0.08
    istring
    -0.08
    èĥ½åĬĽå»ºè®¾
    -0.08
    个人æĪĸ
    -0.08
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.08
    =").
    -0.08
    .INSTANCE
    -0.08
    她表示
    -0.08
    åľ°çº§
    -0.07
    POSITIVE LOGITS
    ä½ľèĢħçļĦ
    0.08
    æĺ¯æĢİæł·
    0.07
    ç»Ĩèħ»
    0.07
    课æĸĩ
    0.07
    çļĦçĶ¨
    0.07
    å·§
    0.07
    主人åħ¬
    0.07
    çªģåĩºäºĨ
    0.07
    “
    0.06
    åħħåĪĨçļĦ
    0.06
    Activations Density 0.001%

    No Known Activations