© 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. 62598
    Prev
    Next
    INDEX
    Explanations

    scientific frameworks and methods

    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
    àµģà´¨àµįനതàµį
    -0.07
    ç«ĭç§ĭ
    -0.07
    éĶĻè¿ĩçļĦ
    -0.07
     اÛĮÙĨÚ©Ùĩ
    -0.06
    ãĤĤãģ®ãģ§
    -0.06
    åķ¸
    -0.06
     anyway
    -0.06
     ÙĨکرد
    -0.06
    ä¸ĢåĬ¨ä¸įåĬ¨
    -0.06
    ãģ¨ãģĦãģĨãģĵãģ¨ãģ§ãģĻ
    -0.06
    POSITIVE LOGITS
    人被
    0.11
    æĹ¥è¢«
    0.10
     emerges
    0.10
     بÛĮشترÛĮ
    0.10
     ensued
    0.10
    çļĦè¯Ħä»·æĺ¯
    0.10
     Äijược
    0.10
    ä¼ļè®®åı¬å¼Ģ
    0.10
    ä¹Łè¢«
    0.10
    å·¥ä½ľè¿Ľè¡ĮäºĨ
    0.10
    Activations Density 1.573%

    No Known Activations