© 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. 44855
    Prev
    Next
    INDEX
    Explanations

    symbolic, spiritual, protection, or leisure

    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
     everywhere
    -0.08
     throughout
    -0.08
    åħ±åIJĮåĬªåĬĽä¸ĭ
    -0.07
    olat
    -0.07
    ä¸įä»ħéľĢè¦ģ
    -0.07
    æĹłæĥħ
    -0.07
     apologise
    -0.07
    verzeichnis
    -0.07
    াপ
    -0.07
    _except
    -0.06
    POSITIVE LOGITS
    æĢ§æĪĸ
    0.17
    人æĪĸ
    0.14
    个人æĪĸ
    0.13
    æŁIJä¸Ģ
    0.13
    æĪĸèĢħæĺ¯
    0.12
    æŁIJ个
    0.12
    æĸĩ件æĪĸ
    0.12
    æŁIJç§į
    0.12
    æĬķèµĦæĪĸ
    0.12
    å·¥ä½ľæĪĸ
    0.12
    Activations Density 0.103%

    No Known Activations