© 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. 14817
    Prev
    Next
    INDEX
    Explanations

    Mark Adler copyright

    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
    arding
    -0.08
    orias
    -0.08
    æĻı
    -0.07
    èĬĴ
    -0.07
    æľĢåIJİæĺ¯
    -0.07
    usel
    -0.07
    AppBundle
    -0.07
    æľ¬æĸĩ为åįļ主
    -0.07
    гази
    -0.07
     rừng
    -0.07
    POSITIVE LOGITS
    \_
    0.08
    磫
    0.07
    ä¹ĺæ³ķ
    0.07
    ${
    0.06
    ahn
    0.06
     Moran
    0.06
    å·§
    0.06
    	  ↵
    0.06
     $
    0.06
    ogg
    0.06
    Activations Density 0.005%

    No Known Activations