© 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. 40867
    Prev
    Next
    INDEX
    Explanations

    proteinuria and nephropathy

    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
    hel
    -0.08
    erot
    -0.07
    æĸ°èĢģ客æĪ·
    -0.07
     locations
    -0.07
     lif
    -0.07
    æ°¢èĥ½
    -0.06
    æĪijæĿ¥è¯´
    -0.06
    ä¸ĢåĪ»
    -0.06
    å¿ĺè®°å¯Ĩçłģ
    -0.06
    vox
    -0.06
    POSITIVE LOGITS
    å¸ļ
    0.08
     лейко
    0.08
    å°¿
    0.08
    æĹ©
    0.08
    èĽĭçĻ½
    0.07
    æ£Ģæµĭ
    0.07
    é¢ľ
    0.07
     roule
    0.07
    Stride
    0.07
    æ¼ı
    0.07
    Activations Density 0.026%

    No Known Activations