© 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. 63621
    Prev
    Next
    INDEX
    Explanations

    programming keywords and symbols

    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
    عÙĬÙĨ
    -0.08
    ↵↵    ↵
    -0.07
    engi
    -0.06
    æĽ´ä¸įä¼ļ
    -0.06
     Schmidt
    -0.06
    ernel
    -0.06
    oport
    -0.06
    etlen
    -0.06
    æı´çĸĨ
    -0.06
    zna
    -0.06
    POSITIVE LOGITS
    ł
    0.08
    astian
    0.07
    ä¸ĢåĪ»
    0.07
    onsense
    0.07
    appings
    0.07
     ëĤĺìĻĶ
    0.07
    äh
    0.07
    Ľ
    0.06
    çŃĨ
    0.06
    ä¸Ģç¬Ķ
    0.06
    Activations Density 0.160%

    No Known Activations