© 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. 27412
    Prev
    Next
    INDEX
    Explanations

    nicely

    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
    ä¹Łåı¯ä»¥æĺ¯
    -0.08
    è¿Ļè¯Ŀ
    -0.08
    è¦ģæĥ³
    -0.08
    æīĢ以è¦ģ
    -0.07
    æĸ¼æĺ¯
    -0.07
    ubat
    -0.07
    exter
    -0.07
     lho
    -0.07
    ujan
    -0.07
    常çĶ¨çļĦ
    -0.07
    POSITIVE LOGITS
     Cruc
    0.08
    åı¯è´µ
    0.07
    este
    0.06
    anness
    0.06
    IRO
    0.06
    æĹłåģ¿çĮ®è¡Ģ
    0.06
    ä¼ģ
    0.06
    idamente
    0.06
    Excellent
    0.06
    æ¯ĶæĪij
    0.06
    Activations Density 0.004%

    No Known Activations