© 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. 19122
    Prev
    Next
    INDEX
    Explanations

    official entities and actions

    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
    arkan
    -0.07
    æĶ¯éĺŁ
    -0.07
    å·¥ç¨ĭéĻ¢éĻ¢å£«
    -0.07
    åłª
    -0.07
    æ½®
    -0.07
    åįıä¼ļä¼ļåijĺ
    -0.07
    ä¸ŃåĽ½è¯ģçĽijä¼ļ
    -0.07
    åī¯çľģéķ¿
    -0.07
    éŃĶçİĭ
    -0.07
     himself
    -0.07
    POSITIVE LOGITS
     itself
    0.11
    é«ĺå±Ĥ
    0.10
    åĨħéĥ¨çļĦ
    0.10
    åħ§éĥ¨
    0.09
    åĩºåĵģçļĦ
    0.09
    åĨħéĥ¨
    0.09
    é«ĺå®ĺ
    0.09
    èªĩãĤĭ
    0.08
    派人
    0.08
    人马
    0.08
    Activations Density 0.911%

    No Known Activations