© 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. 19325
    Prev
    Next
    INDEX
    Explanations

    military policy 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
    æľ¬ç½ij
    -0.08
    моÑģков
    -0.08
     nghá»ģ
    -0.07
    度é«ĺ
    -0.07
    atables
    -0.07
    endu
    -0.07
    endent
    -0.07
    ools
    -0.07
    ì½Ķ리ìķĦ
    -0.07
    ä»Ķ
    -0.07
    POSITIVE LOGITS
    åĴĮæĶ¿åºľ
    0.08
    åIJİçĽ¾
    0.07
    ĸ
    0.07
    ä½ĵéŃĦ
    0.07
    大éĻ¢
    0.07
    /pol
    0.07
    åĴĮçĶŁæ´»
    0.07
    åĴĮæĶ¿æ²»
    0.07
    -backed
    0.06
    åıĬ家éķ¿
    0.06
    Activations Density 0.054%

    No Known Activations