© 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. 19577
    Prev
    Next
    INDEX
    Explanations

    hexadecimal codes or url prefixes

    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
    auer
    -0.07
    ilé
    -0.07
    ram
    -0.07
    å¾Ĺ主
    -0.06
    ilu
    -0.06
    ibi
    -0.06
    åģľæ»ŀ
    -0.06
    å¤ı天
    -0.06
    主è¦ģæĺ¯
    -0.06
    /exp
    -0.06
    POSITIVE LOGITS
    ionalmente
    0.08
    igest
    0.08
    iones
    0.07
    enate
    0.07
    allery
    0.07
    æĹ¥æĹ¥
    0.07
    èĩªè¯Ń
    0.07
    ulton
    0.07
    olute
    0.07
    à¹ĩà¸Ń
    0.07
    Activations Density 0.003%

    No Known Activations