© 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. 55424
    Prev
    Next
    INDEX
    Explanations

    conditions, use, things, believe, items, house

    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
    åħ¶èĩªçĦ¶
    -0.08
    axter
    -0.07
    tras
    -0.07
    _COMPARE
    -0.07
    æĽ¾è¯´
    -0.06
    generator
    -0.06
    halb
    -0.06
    çijŀå®ī
    -0.06
    åīį身
    -0.06
    unic
    -0.06
    POSITIVE LOGITS
    æĿ¡ä»¶ä¸ĭçļĦ
    0.09
    è¿ŀäºij
    0.09
    à¸Ĺัà¹īà¸ĩหลาย
    0.08
    人就
    0.08
    ìŀIJëĵ¤ìĿĦ
    0.08
    人è¦ģ
    0.08
    çļĦ人ä¼ļ
    0.08
    èĢħçļĦ
    0.08
    èĢħä¼ĺåħĪ
    0.07
    æĿ¡ä»¶ä¸ĭ
    0.07
    Activations Density 0.652%

    No Known Activations