© 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. 15159
    Prev
    Next
    INDEX
    Explanations

    specific counts from lists

    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
    forge
    -0.07
     Cian
    -0.07
    -door
    -0.06
    ersp
    -0.06
    ETTA
    -0.06
    ần
    -0.06
    ILogger
    -0.06
    lycer
    -0.06
     Cire
    -0.06
    irl
    -0.06
    POSITIVE LOGITS
    åħĪæĺ¯
    0.09
     namely
    0.08
     appunto
    0.08
    ault
    0.08
    é¦ĸåħĪæĺ¯
    0.08
    æĺ¯ä»Ģä¹Īæł·çļĦ
    0.07
    utama
    0.07
     bowiem
    0.07
    èĢĮè¨Ģ
    0.07
    æĹ¢åı¯ä»¥
    0.07
    Activations Density 0.044%

    No Known Activations