© 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. 55379
    Prev
    Next
    INDEX
    Explanations

    training apprentices or trainees

    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
    微信æī«ä¸Ģæī«
    -0.09
    ä¸ŃåĮ»èį¯å¤§åѦ
    -0.08
    ipas
    -0.08
    æĢ§ä»·æ¯Ķé«ĺ
    -0.08
    icola
    -0.08
    halen
    -0.08
    æĸĹç½Ĺ大éĻĨ
    -0.08
    구ìĹŃ
    -0.07
    thu
    -0.07
    okok
    -0.07
    POSITIVE LOGITS
    æĪĸèĢħ说
    0.08
    æĪĸæĺ¯
    0.08
    -
    0.07
     aka
    0.07
     (=
    0.07
    abl
    0.07
    ogy
    0.06
    ä¹Łå°±æĺ¯
    0.06
    umpt
    0.06
    /
    0.06
    Activations Density 2.195%

    No Known Activations