© 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. 62678
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and notation

    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
    æĪij们çļĦ产åĵģ
    -0.07
    ê°±
    -0.07
    losion
    -0.07
    认缴
    -0.07
    arrass
    -0.07
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.07
    ĻĤ
    -0.07
    LOS
    -0.07
    áºŃt
    -0.07
    gd
    -0.07
    POSITIVE LOGITS
    æĨĭ
    0.08
    odom
    0.07
    unia
    0.07
    æľĽ
    0.06
    antha
    0.06
    ÙĦÙĪÙĦ
    0.06
    checks
    0.06
    жда
    0.06
    bsp
    0.06
    ä»Ĺ
    0.06
    Activations Density 0.009%

    No Known Activations