© 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. 11362
    Prev
    Next
    INDEX
    Explanations

    open-ended, Jetty, better

    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
    ATAB
    -0.09
     Äijâu
    -0.08
    elmi
    -0.08
    鸳
    -0.07
     enten
    -0.07
     EITHER
    -0.07
    ibo
    -0.07
    umo
    -0.07
    åIJĦå¼ıåIJĦæł·çļĦ
    -0.07
    ä¸ŀ
    -0.07
    POSITIVE LOGITS
     clearer
    0.09
    çķ¥æĺ¾
    0.08
    åĽłä¸ºå®ĥ
    0.08
    缴æݥ使çĶ¨
    0.08
     cleaner
    0.07
    为好
    0.07
     explicitly
    0.07
    为佳
    0.07
    åĽłä¸ºåħ¶
    0.07
    å¸Ĥè´¢æĶ¿å±Ģ
    0.07
    Activations Density 0.004%

    No Known Activations