© 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. 11204
    Prev
    Next
    INDEX
    Explanations

    frontend, backend, devops

    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
    åĸĭ
    -0.09
    éªı
    -0.08
    ämm
    -0.08
    Ãłng
    -0.08
    åĬłåħ³æ³¨
    -0.08
    éĿŀ常丰å¯Į
    -0.08
    åŃ¦æł¡é¢Ĩ导
    -0.07
    ptest
    -0.07
    尼奥
    -0.07
    çļĦ带é¢Ĩä¸ĭ
    -0.07
    POSITIVE LOGITS
    siz
    0.07
    æīĭ
    0.07
    Insets
    0.07
     realis
    0.06
     Gutenberg
    0.06
     bew
    0.06
    conse
    0.06
    ç«Ł
    0.06
    leter
    0.06
    å®Į
    0.06
    Activations Density 0.462%

    No Known Activations