© 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. 60209
    Prev
    Next
    INDEX
    Explanations

    international relations and diplomacy

    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
    èīºæľ¯åѦéĻ¢
    -0.07
    ult
    -0.07
    éĺ
    -0.07
    ä¸¥æł¼æī§è¡Į
    -0.07
    æľĢå¿«çļĦéĢŁåº¦
    -0.07
    乡ä¸ĭ
    -0.06
    å¿ħé¡»è¿Ľè¡Į
    -0.06
    å¹³æŶçļĦ
    -0.06
    æĬ½è°ĥ
    -0.06
    éĿ¢åIJijåħ¨åĽ½
    -0.06
    POSITIVE LOGITS
    å¤ļè¾¹
    0.10
    åıĭ好
    0.08
     peacefully
    0.08
     mutually
    0.08
    åĢ¡è®®
    0.08
    äºĴæĥł
    0.08
    讲好
    0.08
     mutual
    0.07
    主æĿĥ
    0.07
    å¤§åĽ½
    0.07
    Activations Density 0.043%

    No Known Activations