© 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. 55993
    Prev
    Next
    INDEX
    Explanations

    possessive 's

    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
    主人çļĦ
    -0.07
    åIJį称
    -0.07
    erer
    -0.06
     Ø´Ùħ
    -0.06
    ichter
    -0.06
    åĪ«çļĦ
    -0.06
    ä¸į该
    -0.06
    åĪ©çĽĬ
    -0.06
    enix
    -0.06
     BOTH
    -0.06
    POSITIVE LOGITS
    ells
    0.07
    ests
    0.07
    为人们
    0.07
     sendiri
    0.07
    usan
    0.07
     aforementioned
    0.07
    åѦçĶŁä»¬
    0.07
    åľ¨çº¿åĴ¨è¯¢
    0.07
    æĸ¹æ³ķä¸İ
    0.07
     penchant
    0.07
    Activations Density 0.271%

    No Known Activations