© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23372
    Prev
    Next
    INDEX
    Explanations

    military personnel and ranks

    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
    ä¸ŃåĽ½ç»ıæµİ
    -0.07
     Monster
    -0.07
    å¤įèµĽ
    -0.07
    åħ«ä»Ļ
    -0.07
    erator
    -0.07
     Wizard
    -0.06
    éħµç´ł
    -0.06
    ä¼ģé¹ħ
    -0.06
     Diablo
    -0.06
    æķĻ主
    -0.06
    POSITIVE LOGITS
     military
    0.14
     Military
    0.13
     infantry
    0.13
     militar
    0.12
    Military
    0.12
     barracks
    0.12
    åĨĽ
    0.11
     soldiers
    0.11
     commander
    0.11
     command
    0.11
    Activations Density 0.935%

    No Known Activations