© 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. 26256
    Prev
    Next
    INDEX
    Explanations

    made lead

    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¸ĭåIJĮ
    -0.08
    ä¸Ĭ马
    -0.07
    Æ¡
    -0.06
    æĪŁ
    -0.06
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.06
    æĪij们è¿ĻäºĽ
    -0.06
     segi
    -0.06
    æº
    -0.06
     damal
    -0.06
    .asInstanceOf
    -0.06
    POSITIVE LOGITS
    ï¸
    0.08
    æŀĹéĢ¸
    0.07
    åĬłè½½æĽ´å¤ļ
    0.07
    ､
    0.07
    ClientRect
    0.07
    }-{
    0.07
    canf
    0.07
    çĥŃéŨæݨèįIJ
    0.07
    )":
    0.06
    éĸĴ
    0.06
    Activations Density 0.472%

    No Known Activations