© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11748
    Prev
    Next
    INDEX
    Explanations

    corporate entities and their executives

    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
    æķĻç§ij书
    -0.08
    nowrap
    -0.08
    kening
    -0.08
    çĻ¾ç§ijåħ¨ä¹¦
    -0.07
    åIJĦèī²
    -0.07
    大家éĥ½çŁ¥éģĵ
    -0.07
    \\/
    -0.07
    utu
    -0.07
    usc
    -0.07
    åIJĦ大
    -0.07
    POSITIVE LOGITS
     proprietary
    0.08
     pilota
    0.07
    own
    0.07
    çļĦå¼Ģåıij
    0.07
    leine
    0.07
     deb
    0.07
     patented
    0.06
     Kickstarter
    0.06
     developed
    0.06
    å¼ĢåıijäºĨ
    0.06
    Activations Density 3.713%

    No Known Activations