© 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. 64782
    Prev
    Next
    INDEX
    Explanations

    AGES, tumors, diseases

    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
    éĩĬ
    -0.06
    åIJĽ
    -0.06
    æ»
    -0.06
     modes
    -0.06
    çļĦä¸įåIJĮ
    -0.06
    keit
    -0.06
     meanings
    -0.06
    ’
    -0.06
    ارات
    -0.06
    lios
    -0.06
    POSITIVE LOGITS
     themselves
    0.10
    inga
    0.09
     Ø£ÙĨÙģسÙĩÙħ
    0.09
    orest
    0.08
    夥
    0.08
    ä¼Ļ
    0.08
    AGMA
    0.08
    رÙĪÙĨ
    0.07
    ä¸Ģç±»
    0.07
    æīĵèµ·
    0.07
    Activations Density 0.511%

    No Known Activations