© 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. 4009
    Prev
    Next
    INDEX
    Explanations

    government departments and agencies

    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
    åĮºå§Ķ书记
    -0.08
    å¸Ĥ人大常å§Ķä¼ļ
    -0.08
    åħ¬åı¸èij£äºĭéķ¿
    -0.07
    ç»Łæ²»èĢħ
    -0.07
    æ´¾åĩºæīĢæ°ijèѦ
    -0.07
    å¸Ĥå§Ķ书记
    -0.07
    å¸ĤæĶ¿åįı
    -0.07
    åľĪ
    -0.07
    碱
    -0.06
    åħ¬åı¸æݨèįIJ
    -0.06
    POSITIVE LOGITS
    èģĮèĥ½
    0.13
    åĨħ设
    0.12
    缴å±ŀ
    0.11
    åIJĦåı¸
    0.11
     divisions
    0.10
    è´Łè´£å¯¹
    0.10
     housed
    0.10
    åīį身
    0.10
    éļ¶å±ŀäºİ
    0.10
     staff
    0.10
    Activations Density 0.211%

    No Known Activations