© 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. 29532
    Prev
    Next
    INDEX
    Explanations

    common practice or likelihood

    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
    ļľ
    -0.08
    elps
    -0.07
    æĹĹ
    -0.07
    ifax
    -0.07
    ÑģÑĤана
    -0.07
    dit
    -0.07
    ়
    -0.07
    ById
    -0.07
    æģ¯
    -0.07
    agrams
    -0.07
    POSITIVE LOGITS
     banget
    0.07
     bowiem
    0.07
     bahwa
    0.07
    ä¸įè¿ĩäºĨ
    0.07
     to
    0.07
    ÙĮ
    0.07
    engah
    0.07
    ä½Ĩæĺ¯è¿Ļ
    0.07
    ä¸įè¿ĩè¿Ļ
    0.06
     sekali
    0.06
    Activations Density 0.376%

    No Known Activations