© 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. 32108
    Prev
    Next
    INDEX
    Explanations

    chemical elements

    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
    _SECTION
    -0.05
     arqu
    -0.05
     fooled
    -0.05
    ä¹ĭçģ«
    -0.05
    ×ķ×Ļ
    -0.05
     lowercase
    -0.05
    zell
    -0.05
    大鱼
    -0.05
     optimum
    -0.05
    ä¸Ń游
    -0.05
    POSITIVE LOGITS
    еÑģпе
    0.09
    åĽ¾æºIJ
    0.09
    cati
    0.08
    丼
    0.08
     întâln
    0.08
    opedia
    0.08
    åıĶ
    0.08
    åĽ¾çīĩæĿ¥æºIJäºİç½ij绾
    0.07
    odiac
    0.07
    orget
    0.07
    Activations Density 0.022%

    No Known Activations