© 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. 49073
    Prev
    Next
    INDEX
    Explanations

    INTRODUCTION or information

    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
    รà¸ĩ
    -0.08
    秣
    -0.07
    imento
    -0.07
    åݦ
    -0.07
    pons
    -0.07
     tint
    -0.07
    举åŁİ
    -0.07
     prem
    -0.07
    utan
    -0.07
    åĪĩå®ŀåı¯è¡ĮçļĦ
    -0.07
    POSITIVE LOGITS
    é¢ĨçĿĢ
    0.08
    èĻı
    0.07
    lify
    0.07
    å·Ŀåİ¿
    0.07
    ä¸įéķ¿
    0.07
     óp
    0.07
    references
    0.07
    ZERO
    0.07
    vue
    0.07
     desarr
    0.07
    Activations Density 0.008%

    No Known Activations