© 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. 22559
    Prev
    Next
    INDEX
    Explanations

    intersection of geometric shapes

    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
    ango
    -0.07
    .cr
    -0.07
    ornado
    -0.07
    bogen
    -0.07
    æ·¹
    -0.07
    exit
    -0.07
     Legge
    -0.07
    uari
    -0.07
    Corn
    -0.07
    娲
    -0.07
    POSITIVE LOGITS
    æĺ¯ä¸¤ä¸ª
    0.10
    locator
    0.09
     shared
    0.08
    åıĮæĸ¹çļĦ
    0.07
    almaz
    0.07
    izr
    0.07
    æī¾ä¸Ģ个
    0.07
     بÙĬÙĨÙĩÙħا
    0.07
     locator
    0.07
    è¿ŀçݯ
    0.07
    Activations Density 0.002%

    No Known Activations