© 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. 26223
    Prev
    Next
    INDEX
    Explanations

    Amorites, monarchies

    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
     unveil
    -0.08
    æ²īæ·Ģ
    -0.07
    åľ¨çİ°åľº
    -0.06
     unwind
    -0.06
    æ½ľæĦıè¯Ĩ
    -0.06
     silen
    -0.06
    æ´ŀ天
    -0.06
     ÑģÑĤоп
    -0.06
    åħĪçĥĪ
    -0.06
    æĪIJ羣
    -0.06
    POSITIVE LOGITS
    åĬ¿åĬĽ
    0.10
    é¦ĸé¢Ĩ
    0.10
    åĭ¢åĬĽ
    0.09
     mercenaries
    0.09
    åĬ¿åĬĽçļĦ
    0.09
    èĩªç«ĭ
    0.09
     instability
    0.09
    åij¨è¾¹çļĦ
    0.09
    å¨ģèĥģ
    0.09
     neighboring
    0.09
    Activations Density 0.148%

    No Known Activations