© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7009
    Prev
    Next
    INDEX
    Explanations

    part of, humans, mankind, goals, type, problems

    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
    Negative Logits
    为该
    -0.10
    该款
    -0.09
    åĪĽä¸ĭ
    -0.09
     diplom
    -0.09
    对该
    -0.08
    ÐIJÐł
    -0.08
    对äºİè¿Ļ个
    -0.08
    å°Ĩ该
    -0.08
    ä¸īå¹´åĨħ
    -0.08
    ä¸īå¹´çļĦ
    -0.08
    POSITIVE LOGITS
    人类社ä¼ļ
    0.10
    ä¸ĩçī©
    0.10
    对人类
    0.10
    æĺ¯äººç±»
    0.09
    æĹłå¤Ħä¸įåľ¨
    0.09
     humans
    0.09
     mankind
    0.09
    人类çļĦ
    0.09
    æĬ½è±¡
    0.09
     Aristotle
    0.09
    Activations Density 0.372%

    No Known Activations