© 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. 26510
    Prev
    Next
    INDEX
    Explanations

    navigate, select, or click

    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
    åĪ°æѤ
    -0.07
    æĿ¿å¼ı
    -0.07
     too
    -0.07
    ä¸įçŁ¥æīĢ
    -0.07
     sem
    -0.07
    placer
    -0.06
    åħ¶å®ĥåªĴä½ĵ
    -0.06
    æľīè¿ĩ
    -0.06
    ä¸įçŁ¥
    -0.06
    æĸ°ä¹¦æݨèįIJ
    -0.06
    POSITIVE LOGITS
    emen
    0.08
    ä¸Ģæİ¢
    0.08
     Locate
    0.07
    ä¸ĩæĪ·
    0.07
     locate
    0.07
    ürg
    0.07
    /browse
    0.07
    ggia
    0.07
    /find
    0.07
    Fra
    0.07
    Activations Density 0.089%

    No Known Activations