© 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. 48377
    Prev
    Next
    INDEX
    Explanations

    integral patterns or terms

    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
    波波
    -0.07
    ived
    -0.07
    ivec
    -0.07
    owoÅĽci
    -0.07
     láng
    -0.07
    ZO
    -0.07
    ×IJר
    -0.07
    æĿ¥æŶ
    -0.06
    秫
    -0.06
    hoven
    -0.06
    POSITIVE LOGITS
    ذا
    0.07
     thunk
    0.07
    迹
    0.07
     raping
    0.07
     sums
    0.07
     Fad
    0.07
    meal
    0.07
    åħ´åįİ
    0.06
    خاÙĨÙĩ
    0.06
     Thom
    0.06
    Activations Density 0.008%

    No Known Activations