© 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. 64927
    Prev
    Next
    INDEX
    Explanations

    broader, wider, inclusive scope

    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
    anko
    -0.07
    anty
    -0.07
    æ¸ħæ¸ħ
    -0.07
    lden
    -0.07
     clear
    -0.07
    ä¿±è¿Ľ
    -0.06
    ½Ķ
    -0.06
    _stylesheet
    -0.06
    ä¸įåı¯åıĬ
    -0.06
    _clear
    -0.06
    POSITIVE LOGITS
     broader
    0.20
    ä¸įéĻIJäºİ
    0.17
    ä¸įéĻIJ
    0.16
    æ³ĽæĮĩ
    0.16
     wider
    0.15
    广ä¹ī
    0.15
    ä¸įä¸Ģå®ļæĺ¯
    0.14
    ä¸įä¸Ģå®ļ
    0.14
     widest
    0.13
     inclusive
    0.13
    Activations Density 0.125%

    No Known Activations