© 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. 56797
    Prev
    Next
    INDEX
    Explanations

    language and locale settings

    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
    htt
    -0.07
    anova
    -0.07
    åĨ³
    -0.07
    æľīå½¢
    -0.07
    WithContext
    -0.07
    å·²åĪ°
    -0.07
    soever
    -0.07
    BSD
    -0.07
    å¼ı设计
    -0.07
    ä¸įåĩı
    -0.07
    POSITIVE LOGITS
     dialect
    0.09
     locales
    0.08
    åħ¼å®¹
    0.07
    -compatible
    0.07
     пÑĢедпоÑĩиÑĤа
    0.07
    fallback
    0.07
     chosen
    0.07
     Neutral
    0.07
     fallback
    0.07
    åģı好
    0.07
    Activations Density 0.266%

    No Known Activations