© 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. 28310
    Prev
    Next
    INDEX
    Explanations

    medical conditions and states

    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
    eday
    -0.08
    ä»ħä»£è¡¨ä½ľèĢħ
    -0.08
    enius
    -0.08
    ayan
    -0.08
    ppo
    -0.07
    ä¾Ľç¨¿
    -0.07
    æĤ£äºĨ
    -0.07
    à¸Ĵ
    -0.07
    ece
    -0.07
     Mehmet
    -0.07
    POSITIVE LOGITS
    Descriptors
    0.07
    éĺĸ
    0.07
    ÑĨÑİ
    0.06
    .datab
    0.06
    mog
    0.06
    zure
    0.06
    亦æĺ¯
    0.06
     Dung
    0.06
    åľ£ç»ı
    0.06
    ä¹Łæĺ¯ä¸Ģæł·
    0.06
    Activations Density 0.583%

    No Known Activations