© 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. 39423
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers

    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
    ãĥ©ãĥł
    -0.07
    èIJĿåįľ
    -0.07
    ä¼¼
    -0.07
    imized
    -0.07
    uts
    -0.06
    è¦ģåĪ°
    -0.06
    롱
    -0.06
    inkt
    -0.06
    ems
    -0.06
    _dispatch
    -0.06
    POSITIVE LOGITS
    bund
    0.08
    noop
    0.07
    缮åīįæŃ£åľ¨
    0.07
    ç«ŀ
    0.07
    åŦ
    0.07
    æģº
    0.07
    姥
    0.07
    aglia
    0.07
    æ´Ľä¼Ĭ
    0.07
    ãĤ«ãĥª
    0.07
    Activations Density 0.019%

    No Known Activations