© 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. 11947
    Prev
    Next
    INDEX
    Explanations

    patent document numbers

    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
    пÑı
    -0.08
    asai
    -0.07
    ¨
    -0.07
    解æĶ¾
    -0.07
     sangatlah
    -0.07
     recol
    -0.07
    æĪIJç«ł
    -0.06
    дÑı
    -0.06
     Biel
    -0.06
    åĤ¾
    -0.06
    POSITIVE LOGITS
    æľ¬åıijæĺİ
    0.06
    ä¸Ń飩
    0.06
    erson
    0.06
    æľ¬çīĩ
    0.06
    eves
    0.06
    ç¥IJ
    0.06
    outer
    0.06
    æľ¬åıijæĺİçļĦ
    0.06
    èµIJ
    0.06
     Corea
    0.06
    Activations Density 0.003%

    No Known Activations