© 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. 39188
    Prev
    Next
    INDEX
    Explanations

    Zhengzhou, POSIX, Chinese characters

    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
    eting
    -0.08
    Úĵ
    -0.08
    tober
    -0.08
    å¿ĺè¿Ķ
    -0.08
    zelf
    -0.08
    à¦ģ
    -0.08
    à¦ĸন
    -0.08
    issement
    -0.08
    สิà¹īà¸Ļ
    -0.08
    źdz
    -0.08
    POSITIVE LOGITS
    leger
    0.08
    ãģĹãģıãģ¯
    0.07
    illions
    0.07
    ivals
    0.07
    ä¸įè¡°
    0.06
    enance
    0.06
    ational
    0.06
    Ø·
    0.06
    ongyang
    0.06
    ÙħÙĪ
    0.06
    Activations Density 0.004%

    No Known Activations