© 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. 20822
    Prev
    Next
    INDEX
    Explanations

    various Chinese characters

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    lain
    -0.06
    ucha
    -0.06
    åĴĮéĶĢåĶ®
    -0.06
    ÃŃž
    -0.06
     Fashion
    -0.06
    atable
    -0.06
    ãĢIJ
    -0.06
    è®¤çľŁçļĦ
    -0.06
    壤
    -0.06
    POSITIVE LOGITS
    äººä¹Ł
    0.08
    åĬłä¹ĭ
    0.08
    åİĭåĬĽå¤§
    0.08
    ãģĭãģ¤
    0.08
    åıĸèĢĮ代ä¹ĭ
    0.08
    IMS
    0.08
    人æ°ijçĶŁæ´»
    0.07
    æ»ĭçĶŁ
    0.07
    æĶ¯æĮģåĬĽåº¦
    0.07
    éĶĻè¿ĩ
    0.07
    Activations Density 0.009%

    No Known Activations