© 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. 14694
    Prev
    Next
    INDEX
    Explanations

    legal and particularly academic contexts

    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
    precated
    -0.08
    awan
    -0.08
    ç«Łæĺ¯
    -0.07
    ÅĤaw
    -0.07
     eikä
    -0.07
    eko
    -0.07
    äºĮ次
    -0.07
    æ¯Ķä¾ĭ为
    -0.07
    odon
    -0.07
    resto
    -0.07
    POSITIVE LOGITS
    以ä¸ĭæĺ¯ä¸ĢäºĽ
    0.09
     aspects
    0.08
    许许å¤ļå¤ļçļĦ
    0.08
    åı¯ä»¥ä»İ
    0.08
    主è¦ģä»İ
    0.08
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.07
    以ä¸ĭåĨħ容
    0.07
    åIJĦæĸ¹éĿ¢çļĦ
    0.07
    Extend
    0.07
    以ä¸ĭåĩłçĤ¹
    0.07
    Activations Density 0.006%

    No Known Activations