© 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. 21489
    Prev
    Next
    INDEX
    Explanations

    smallest n such that

    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
    uels
    -0.07
    utip
    -0.07
    çī¹æĦı
    -0.06
    ammel
    -0.06
    åīį车
    -0.06
     quite
    -0.06
    éĿŀ常æĸ¹ä¾¿
    -0.06
    ÑĤÑĩ
    -0.06
    å°ıé¾Ļ
    -0.06
    æĢİä¹Īå¤ĦçIJĨ
    -0.06
    POSITIVE LOGITS
    åĴĮæľĢ
    0.08
    ä¹Łæĺ¯
    0.08
    åħ¨åĬĽä»¥èµ´
    0.07
    çŃ¹
    0.07
    ihak
    0.07
    ç½¢äºĨ
    0.07
    ä¹Łæĺ¯æľĢ
    0.07
     ooit
    0.07
    eward
    0.07
     quals
    0.07
    Activations Density 0.022%

    No Known Activations