© 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. 39573
    Prev
    Next
    INDEX
    Explanations

    as followed by definitions or descriptions

    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
    orse
    -0.07
    æĺ¯åĽłä¸º
    -0.07
    ùy
    -0.07
    erma
    -0.07
    æĺ¯çĶ±äºİ
    -0.07
    ãģ¡ãģª
    -0.06
    æĺ¯ä¸ºäºĨ
    -0.06
    åľ¨åIJĮ
    -0.06
    çIJĨçĶ±
    -0.06
    ×ķ×ļ
    -0.06
    POSITIVE LOGITS
     defined
    0.09
    åıĬåħ¶åºĶçĶ¨
    0.08
    defined
    0.08
    å¤ļç§įå½¢å¼ı
    0.08
    Defined
    0.08
    odb
    0.08
    cribed
    0.08
     expressed
    0.08
    ŀ
    0.07
    å²ij
    0.07
    Activations Density 0.067%

    No Known Activations