© 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. 17109
    Prev
    Next
    INDEX
    Explanations

    code formatting or symbolic structure

    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
    åݦ
    -0.08
    çĽ¸å¯¹çļĦ
    -0.07
    è²Į
    -0.07
    ÑĦа
    -0.07
    åľ°äºļ
    -0.07
    essa
    -0.06
    äºĭåħ³
    -0.06
     ÐĿад
    -0.06
    æĩµ
    -0.06
    ãģĹãģĮ
    -0.06
    POSITIVE LOGITS
     okt
    0.07
     GLsizei
    0.07
    cium
    0.07
    irsi
    0.07
    åį¸
    0.07
    kar
    0.07
    è¿Ļ个æķ°åŃĹ
    0.07
    åµĺ
    0.07
    ulp
    0.06
    alem
    0.06
    Activations Density 0.068%

    No Known Activations