© 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. 17129
    Prev
    Next
    INDEX
    Explanations

    we, both, the, four

    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
    æľīæѤ
    -0.09
    hei
    -0.08
    ä¸Ģå®ļç¨ĭ度
    -0.07
    å¦ĤæѤ
    -0.07
    èµĦæĸĻæĺ¾ç¤º
    -0.07
    è¿Ļæĺ¯ä»Ģä¹Ī
    -0.07
    æĶ¯æĮģåĴĮ
    -0.07
    æľīè¿Ļ个
    -0.07
    è´¨éĩı为
    -0.07
    -picker
    -0.07
    POSITIVE LOGITS
    é¦ĸåħĪè¦ģ
    0.09
    é¦ĸåħĪéľĢè¦ģ
    0.09
    两个æĸ¹éĿ¢
    0.08
    两æĸ¹éĿ¢
    0.08
    é¦ĸåħĪ
    0.08
     firstly
    0.08
    çĿĢçľ¼äºİ
    0.08
    以ä¸ĭåĩłä¸ª
    0.08
     ìļ°ìĦł
    0.08
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.07
    Activations Density 0.067%

    No Known Activations