© 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. 23449
    Prev
    Next
    INDEX
    Explanations

    iatric examination or function

    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
    º
    -0.08
    yt
    -0.07
    åįĴ
    -0.07
    logen
    -0.07
    ëŀij
    -0.07
    andone
    -0.07
    oller
    -0.07
    asnya
    -0.07
    yai
    -0.07
    Ø·ÙĤ
    -0.07
    POSITIVE LOGITS
    åı¯ä»¥æľīæķĪåľ°
    0.07
    èĮ
    0.06
    etto
    0.06
    uite
    0.06
    大大çļĦ
    0.06
    etest
    0.06
    pon
    0.06
    igny
    0.06
    kle
    0.06
    rie
    0.06
    Activations Density 1.142%

    No Known Activations