© 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. 34085
    Prev
    Next
    INDEX
    Explanations

    separate or independent instances

    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
    两æĸ¹éĿ¢
    -0.09
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    -0.08
    è¿Ļ两ç§į
    -0.08
    两类
    -0.08
    两项
    -0.07
     som
    -0.07
    è¿Ļ两
    -0.07
    两ç§į
    -0.07
    æŃ£æĺ¯
    -0.07
    æľī两ç§į
    -0.07
    POSITIVE LOGITS
    çĭ¬ç«ĭçļĦ
    0.17
    åIJĦèĩªçļĦ
    0.16
    çĭ¬ç«ĭ
    0.16
     independently
    0.15
    çĭ¬ç«ĭæĢ§
    0.15
    åIJĦèĩª
    0.14
     separate
    0.14
     separately
    0.14
     ëıħ립
    0.13
     independent
    0.13
    Activations Density 0.173%

    No Known Activations