© 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. 40381
    Prev
    Next
    INDEX
    Explanations

    function calls and code syntax

    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
    ä¸Ńä¹ĭ
    -0.07
    第ä¸Ģè½®
    -0.07
    illin
    -0.06
    ä¸įèµ°
    -0.06
    导èĩ´äºĨ
    -0.06
    ysten
    -0.06
     Uncomment
    -0.06
    ä¸įåĩºæĿ¥
    -0.06
    第ä¸Ģ段
    -0.06
    åºĶ该ä¸įä¼ļ
    -0.06
    POSITIVE LOGITS
    	Returns
    0.08
    çĶ¨åľ¨
    0.08
     handy
    0.08
    åĨħç½®
    0.08
    è¿IJç®Ĺ符
    0.08
     nhan
    0.08
     shortcut
    0.07
    éĩijå±±
    0.07
    çĶ¨æ³ķ
    0.07
    帮åĬ©
    0.07
    Activations Density 0.189%

    No Known Activations