© 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. 47710
    Prev
    Next
    INDEX
    Explanations

    political and international affairs

    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
    ellen
    -0.08
     sót
    -0.07
    çIJĨäºĭéķ¿
    -0.07
    éĩĩ
    -0.07
    æĢ¥æĢ¥
    -0.07
     Emer
    -0.07
    欢è¿İåħī临
    -0.07
     emerg
    -0.07
     noble
    -0.07
    设æ³ķ
    -0.07
    POSITIVE LOGITS
    社ä¼ļ主ä¹īçݰ代åĮĸ
    0.09
    åĴĮ人æ°ij
    0.07
    éŃĶç¥ŀ
    0.07
    iland
    0.07
    åĴĮ建设
    0.07
    èĥ½æºIJ
    0.07
    çĻ¾äºĭ
    0.07
    å¯Į强
    0.07
    ettino
    0.07
    çݰ代åĮĸ建设
    0.07
    Activations Density 0.003%

    No Known Activations