© 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. 41629
    Prev
    Next
    INDEX
    Explanations

    East Asian characters

    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
    auge
    -0.07
     Wi
    -0.07
    ambah
    -0.07
    ãĥ¼ãĤ¸ãĥ¥
    -0.07
    ault
    -0.06
    å¦Ĥ梦
    -0.06
    Wi
    -0.06
    åĩ»
    -0.06
    èĴĻ
    -0.06
    WB
    -0.06
    POSITIVE LOGITS
    ä¹ŁæľīäºĨ
    0.09
     ÑĤоже
    0.09
    è¿Ľä¸ĢæŃ¥å¢ŀ强
    0.09
     nữa
    0.09
    ä¹Łåıĺå¾Ĺ
    0.09
    ä¹Łå¯¹
    0.08
    åı¦ä¸Ģè¾¹
    0.08
    çĦ¶å¤§
    0.08
    ä¹Łéļıä¹ĭ
    0.08
    è¿Ľä¸ĢæŃ¥æĺİç¡®
    0.08
    Activations Density 0.002%

    No Known Activations