© 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. 37997
    Prev
    Next
    INDEX
    Explanations

    Chinese and non-English words

    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
    onger
    -0.08
    ationToken
    -0.08
    alian
    -0.07
    äºĮä¸ĸ
    -0.07
    ervi
    -0.07
    alte
    -0.07
    alan
    -0.07
    太éĥİ
    -0.07
    æĸ°ç¤¾
    -0.07
    taki
    -0.07
    POSITIVE LOGITS
    каз
    0.09
    ä¹ĭä¸ĢçļĦ
    0.08
    rou
    0.07
    ä¹ĭä¸ĭ
    0.07
    dae
    0.07
    ä¹ĭåľ°
    0.07
    estas
    0.07
    ter
    0.07
    зал
    0.07
    quat
    0.07
    Activations Density 0.050%

    No Known Activations