© 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. 38169
    Prev
    Next
    INDEX
    Explanations

    shape and dimensions

    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
    æĢģ
    -0.08
     ÙħÙĨظ
    -0.08
     tán
    -0.07
    车åĨµ
    -0.07
    affected
    -0.07
     Klimas
    -0.07
    emean
    -0.07
    é¢Ĺ
    -0.07
     Chron
    -0.07
    å°¾
    -0.07
    POSITIVE LOGITS
    设计æĸ¹æ¡Ī
    0.08
     пÑĢÑıмоÑĥго
    0.08
     rectangular
    0.08
     optimization
    0.08
     redesign
    0.08
     enclosing
    0.08
     Rect
    0.07
    åij¨éķ¿
    0.07
    éķ¿æĸ¹å½¢
    0.07
     dimensions
    0.07
    Activations Density 0.015%

    No Known Activations