© 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. 27369
    Prev
    Next
    INDEX
    Explanations

    width dimension values

    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
    ale
    -0.07
    maj
    -0.07
    æĦıæĸĻ
    -0.06
    ose
    -0.06
    à¯įதà¯įத
    -0.06
    åĪĨ娩
    -0.06
    绪
    -0.06
     Kaj
    -0.06
    æĪijæ°¸è¿ľ
    -0.06
    ifu
    -0.06
    POSITIVE LOGITS
    宽
    0.08
     width
    0.08
    _width
    0.08
    width
    0.08
    寬
    0.08
    Width
    0.08
    	width
    0.08
    ÙĩاÙĨ
    0.07
    (width
    0.07
    æĶ¾ä¸įä¸ĭ
    0.07
    Activations Density 0.137%

    No Known Activations