© 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. 25430
    Prev
    Next
    INDEX
    Explanations

    energy worldwide

    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
    åı¯è¨Ģ
    -0.08
    ä¹ĭ称
    -0.08
    便å¼Ģå§ĭ
    -0.07
    æĪijåIJĹ
    -0.07
    çĦ¶èĢĮ
    -0.06
    çļĦåIJĹ
    -0.06
    æķħèĢĮ
    -0.06
    çļĦ人äºĨ
    -0.06
     ello
    -0.06
    itera
    -0.06
    POSITIVE LOGITS
    éĩįçĤ¹æĺ¯
    0.09
    æĪIJåĪĨæĺ¯
    0.09
    ç»ıèIJ¥èĮĥåĽ´åĮħæĭ¬
    0.08
    åĬĽãģ¯
    0.08
    æľĢåIJİæĺ¯
    0.08
    æľĢ广
    0.08
    æĸ¹å¼ıæĺ¯
    0.08
    дÑİ
    0.07
    åĨħ容æľī
    0.07
    ible
    0.07
    Activations Density 0.010%

    No Known Activations