© 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. 58645
    Prev
    Next
    INDEX
    Explanations

    light interference or signal injection

    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
    _conversion
    -0.08
     kiêm
    -0.07
    åĨħéľĢ
    -0.06
    ä¸Ģè½®
    -0.06
    å¤ĸ人
    -0.06
    ç¹ģèį£æĺĮ缼
    -0.06
    ä¸ī人
    -0.06
    umo
    -0.06
    åIJijèį£
    -0.06
    Limits
    -0.06
    POSITIVE LOGITS
    æĺ¯æĿ¥èĩª
    0.09
    æĿ¥èĩª
    0.09
     streams
    0.09
     timing
    0.09
     contributions
    0.09
    ä¾Ĩèĩª
    0.09
     sources
    0.09
    å»¶è¿Ł
    0.09
    天ä»Ļ
    0.08
    -source
    0.08
    Activations Density 0.024%

    No Known Activations