© 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. 24797
    Prev
    Next
    INDEX
    Explanations

    treaties and peace treaties

    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
    orida
    -0.09
     florida
    -0.08
    ÃŃp
    -0.08
    转ä¸ļ
    -0.08
    èģĶåĤ¨
    -0.08
    èĢĺ
    -0.08
    ÃŃb
    -0.07
     Palma
    -0.07
    íĴĢ
    -0.07
    Powered
    -0.07
    POSITIVE LOGITS
    ä¾µçķ¥
    0.10
    款
    0.09
     treaty
    0.08
    交æ¶ī
    0.08
    è¾±
    0.08
     Treaty
    0.08
    å±Ī
    0.08
     treaties
    0.08
    ä¸įå±Ī
    0.08
    æĿ¡çº¦
    0.07
    Activations Density 0.010%

    No Known Activations