© 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. 19937
    Prev
    Next
    INDEX
    Explanations

    interior and exterior places

    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
    jol
    -0.08
    çļĦåľºæīĢ
    -0.07
    åŁİå¸Ĥä¸Ń
    -0.07
    èĩªèº«
    -0.07
    梦ä¸Ń
    -0.06
    ä¹ĭ为
    -0.06
    æ¯Ķæĸ¹
    -0.06
    å¾Ĺ以
    -0.06
    æķĻäºİ
    -0.06
    ó
    -0.06
    POSITIVE LOGITS
     vắng
    0.08
    åŃIJéĩĮ
    0.08
    åıijèµ·äºĨ
    0.07
    INCI
    0.07
    æľŁå¾ħæĤ¨çļĦ
    0.07
    _nth
    0.07
    boden
    0.07
     تارÛĮ
    0.07
    åľ¨å¼Ģå±ķ
    0.07
    CTest
    0.07
    Activations Density 0.197%

    No Known Activations