© 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. 11996
    Prev
    Next
    INDEX
    Explanations

    date property, ms.date

    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
    inder
    -0.07
    uben
    -0.06
    chnik
    -0.06
    æľīåħ¶
    -0.06
    åįĵ
    -0.06
    çĺŁ
    -0.06
    ä¼ı天
    -0.06
     Willi
    -0.06
    éľĦ
    -0.06
    åħļç»Ħ书记
    -0.06
    POSITIVE LOGITS
    æľĢæĸ°è¯Ħ论
    0.08
    æľĢç»ĪçļĦ
    0.08
    åºĶæĢ¥é¢Ħæ¡Ī
    0.08
    çķĻæĦı
    0.08
    æĶ¿çŃĸåĴĮ
    0.08
    ä¸ĭä¸ĢæĿ¡
    0.08
     ultimately
    0.08
    ä¹ĭæľĢ
    0.08
    ykl
    0.08
    æ¯ıä¸Ģ个人çļĦ
    0.08
    Activations Density 0.004%

    No Known Activations