© 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. 1392
    Prev
    Next
    INDEX
    Explanations

    championship standings or locomotive summary

    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
     certain
    -0.07
    Certain
    -0.07
    æľīæĿ¡ä»¶çļĦ
    -0.07
    InstanceOf
    -0.07
    以åıĬ
    -0.06
    ÛķÙĪÛķ
    -0.06
    æĪĸå¤ļ个
    -0.06
    eldon
    -0.06
    çĩĥ
    -0.06
    forth
    -0.06
    POSITIVE LOGITS
     vs
    0.12
    ìĿ´ëŀĢ
    0.09
     versus
    0.08
     overview
    0.08
    åľ¨è¿Ļæł·çļĦ
    0.08
    å°ıçŁ¥è¯Ĩ
    0.08
    ãģ¨ãģĦãģĨãģ¨
    0.07
     considerations
    0.07
    ////////////////////////////////////////////////////////////////
    0.07
    æĥħåĨµåĪĨæŀIJ
    0.07
    Activations Density 0.118%

    No Known Activations