© 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. 14069
    Prev
    Next
    INDEX
    Explanations

    medical characteristic distinguishing features

    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
    lips
    -0.07
    (getContext
    -0.07
    nia
    -0.07
     Lain
    -0.07
    ulang
    -0.07
     PARTICULAR
    -0.07
    害
    -0.07
    umon
    -0.07
    един
    -0.07
    æµİå®ģå¸Ĥ
    -0.07
    POSITIVE LOGITS
     characteristic
    0.09
     hallmark
    0.09
    è¿Ļä¹Łæĺ¯
    0.08
    åħ¸åŀĭ
    0.08
    åħ¸åŀĭçļĦ
    0.07
     typical
    0.07
    åľ¨è¿Ļç§į
    0.07
     accompanies
    0.07
    为äºĨå®ŀçİ°
    0.07
     khas
    0.07
    Activations Density 0.291%

    No Known Activations