© 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. 25649
    Prev
    Next
    INDEX
    Explanations

    trigonometric substitution variables

    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
    inggu
    -0.07
    åħ¼æĢ»ç»ıçIJĨ
    -0.07
     Weih
    -0.07
     yanı
    -0.07
    æ»ĵ
    -0.06
    плÑİ
    -0.06
     Humb
    -0.06
    megen
    -0.06
    éĹĨ
    -0.06
    ½Ķ
    -0.06
    POSITIVE LOGITS
    ä¸ĸçķĮ
    0.08
    åĮĸå¤ĦçIJĨ
    0.07
    åıĺæį¢
    0.07
    åĮĸåĴĮ
    0.07
     menj
    0.07
    转åĮĸçļĦ
    0.07
     ë³ĢíĻĺ
    0.07
    转æį¢
    0.07
    åĮĸ
    0.07
    aday
    0.07
    Activations Density 0.004%

    No Known Activations