© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30519
    Prev
    Next
    INDEX
    Explanations

    Hansen Brothers

    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
    åľ¨çº¿åĴ¨è¯¢
    -0.07
    éb
    -0.07
     باÙĨ
    -0.07
    atorie
    -0.07
    ä¿¡ä¸Ń
    -0.07
    ondes
    -0.07
    /logging
    -0.07
    ม
    -0.07
    åıĸç¼Ķ
    -0.07
    æŃ£æĺ¯åľ¨
    -0.07
    POSITIVE LOGITS
    gie
    0.07
    è¿Ļä¹Īä¸Ģ个
    0.07
    ä¸ĭåIJĮ
    0.07
    ä¸ĢåĪ°
    0.07
     somehow
    0.07
     sop
    0.07
    еÑģа
    0.07
    atura
    0.06
    olto
    0.06
    ursor
    0.06
    Activations Density 0.085%

    No Known Activations