© 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. 65233
    Prev
    Next
    INDEX
    Explanations

    output or answer

    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
    广åijĬæľįåĬ¡
    -0.09
     overd
    -0.07
    缸åħ³èµĦ讯
    -0.07
    _partial
    -0.07
    elus
    -0.07
    æľ¬ç½ijç«Ļ
    -0.07
    legates
    -0.07
    ä»ĸ家
    -0.07
    irman
    -0.07
    åħ¬åı¸æĸ°éĹ»
    -0.07
    POSITIVE LOGITS
    æł¼å¼ı
    0.08
     format
    0.08
    产åĩº
    0.08
    format
    0.07
     drawer
    0.07
    ola
    0.07
    æł¼å¼ıåĮĸ
    0.07
     sapi
    0.07
    产
    0.07
    å¸
    0.07
    Activations Density 0.005%

    No Known Activations