© 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. 55790
    Prev
    Next
    INDEX
    Explanations

    printer drivers

    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
    omy
    -0.06
    å¯Ħ
    -0.06
    bars
    -0.06
    _launcher
    -0.06
    arna
    -0.06
     Mall
    -0.05
    åįķ
    -0.05
    åĽº
    -0.05
    åĩºæģ¯
    -0.05
    ä¸Ńå°ı
    -0.05
    POSITIVE LOGITS
    ä¹Łæĺ¯å¾Ī
    0.09
    ãģĵãģ¡ãĤīãĤĤ
    0.09
     similarly
    0.09
    ä»Ĭ度ãģ¯
    0.09
     ebenfalls
    0.08
    åIJĮæł·
    0.08
    .Promise
    0.08
    chst
    0.08
    ToObject
    0.08
    chal
    0.08
    Activations Density 0.147%

    No Known Activations