© 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. 29846
    Prev
    Next
    INDEX
    Explanations

    medical terms and body parts

    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
    irq
    -0.07
    rike
    -0.07
     boc
    -0.06
    æ·¼
    -0.06
    /color
    -0.06
    isque
    -0.06
    æĸī
    -0.06
    à¸IJ
    -0.06
    elay
    -0.06
    пÑĢÑĭ
    -0.06
    POSITIVE LOGITS
    xim
    0.08
    åģĩå®ļ
    0.08
    æĺ¯æĮī
    0.08
    akon
    0.07
    лÑıÑĤ
    0.07
     غاÙĦب
    0.07
    æĺ¯æĮīçħ§
    0.07
    schuh
    0.07
    çľĭæĪIJ
    0.07
    人åĿĩ
    0.07
    Activations Density 0.019%

    No Known Activations