© 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. 39562
    Prev
    Next
    INDEX
    Explanations

    initialisms or abbreviations

    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
    agi
    -0.07
    داÙĨ
    -0.07
    罪çļĦ
    -0.06
    mast
    -0.06
     Mast
    -0.06
    plat
    -0.06
    罪
    -0.06
    ette
    -0.06
    unic
    -0.06
     pro
    -0.06
    POSITIVE LOGITS
    _permalink
    0.09
    /Graphics
    0.08
    ãĥ³ãĥĪ
    0.08
    çĽ¸ä¼¼æĸĩçĮ®
    0.08
    ecke
    0.07
    æĶ¿æ³ķ大åѦ
    0.07
     duyên
    0.07
     Schulter
    0.07
    etil
    0.07
    semb
    0.07
    Activations Density 0.210%

    No Known Activations