© 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. 57909
    Prev
    Next
    INDEX
    Explanations

    same or similarly

    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
    åıªä»£è¡¨
    -0.08
    pas
    -0.07
     THEN
    -0.07
    avigator
    -0.07
    /repos
    -0.07
     Äijá»Ŀi
    -0.07
    çĶŁæ´»åľ¨
    -0.06
    oje
    -0.06
    ä¼ļæľīå¾Īå¤ļ
    -0.06
    оÑĤов
    -0.06
    POSITIVE LOGITS
    åIJĮæł·
    0.26
    åIJĮæł·çļĦ
    0.25
    åIJĮ樣
    0.23
    åIJĮæł·æĺ¯
    0.23
     same
    0.21
     similarly
    0.21
     Same
    0.20
    åIJĮä¸Ĭ
    0.20
    same
    0.19
     likewise
    0.19
    Activations Density 0.097%

    No Known Activations