© 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. 64673
    Prev
    Next
    INDEX
    Explanations

    medical and scientific descriptions

    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
    å¼Ģ好
    -0.07
    宵
    -0.07
    رÙĬÙĨ
    -0.06
     ilusión
    -0.06
    ohner
    -0.06
    æĬĵç´§æŶéĹ´
    -0.06
    _VC
    -0.06
    िर
    -0.06
    Po
    -0.06
    æ±łä¸Ń
    -0.06
    POSITIVE LOGITS
    idler
    0.08
    Ħ
    0.07
    ieu
    0.07
     sekaligus
    0.07
    itt
    0.07
    æĸ¹éĿ¢çļĦ
    0.07
    åıĪåı¯ä»¥
    0.07
    دا
    0.07
    ifer
    0.06
    asure
    0.06
    Activations Density 0.130%

    No Known Activations