© 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. 28144
    Prev
    Next
    INDEX
    Explanations

    that is / are / use / make

    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
    åĪĨå¤ĸ
    -0.08
    ãģ¾ãģĦ
    -0.08
    gio
    -0.08
    æĺ¯ä¸Ģ项
    -0.07
    NECT
    -0.07
    è¿Ļæĺ¯ä¸Ģç§į
    -0.07
    æīĢåIJij
    -0.07
    æĺ¯ä¸Ģç§įéĿŀ常
    -0.07
    ä¸Ģå¦Ĥ
    -0.07
     suffice
    -0.07
    POSITIVE LOGITS
    缴æİ¥æĪĸéĹ´æİ¥
    0.10
    èĥ½çĶ¨
    0.09
     either
    0.08
    æĬķèµĦæĪĸ
    0.08
     ones
    0.07
     alguna
    0.07
     whose
    0.07
    æĪĸåĽł
    0.07
    éli
    0.07
    èij©
    0.07
    Activations Density 0.211%

    No Known Activations