© 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. 17511
    Prev
    Next
    INDEX
    Explanations

    list item number

    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
    Ø®ÙĪر
    -0.08
    retch
    -0.07
    åıĸèĢĮ代ä¹ĭ
    -0.07
    è¿Ļç§įçݰ象
    -0.07
    ekar
    -0.07
    tese
    -0.07
    人
    -0.07
    owler
    -0.07
    iesel
    -0.07
    ç§
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.08
    emente
    0.08
    Ùĭا
    0.07
    à¹Į
    0.07
    اÙĭ
    0.07
     à¹Ĩ
    0.07
    а
    0.07
     glor
    0.06
    à¹Ĩ
    0.06
    ly
    0.06
    Activations Density 0.004%

    No Known Activations