© 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. 45658
    Prev
    Next
    INDEX
    Explanations

    military intervention and deployment

    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
    tick
    -0.08
    ä¿ĺèĻı
    -0.07
     ticks
    -0.07
    æıIJ交
    -0.07
    åŃľåŃľ
    -0.07
     trôi
    -0.07
    å¦ĤæĦ¿
    -0.07
     viva
    -0.07
    为满足
    -0.07
    åĸľ
    -0.07
    POSITIVE LOGITS
    ä»ĭåħ¥
    0.11
    赶åĪ°çİ°åľº
    0.11
     protective
    0.11
     intervention
    0.11
    å¹²é¢Ħ
    0.10
    ä¿ĿæĬ¤
    0.10
     intervene
    0.10
    ä¿ĿæĬ¤èĩªå·±çļĦ
    0.10
     protect
    0.10
     protecting
    0.10
    Activations Density 0.218%

    No Known Activations