© 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. 55536
    Prev
    Next
    INDEX
    Explanations

    playing career

    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
    asel
    -0.07
    ÚĺÛĮ
    -0.07
    lings
    -0.07
    _CONDITION
    -0.07
    ritt
    -0.07
    udah
    -0.07
    _vk
    -0.07
    orden
    -0.07
    å©
    -0.07
    él
    -0.07
    POSITIVE LOGITS
    款çļĦ
    0.07
     warta
    0.07
     Keller
    0.06
    akening
    0.06
     equ
    0.06
    ä¾Ŀæ³ķ追究责任
    0.06
    éĿĴéĿĴ
    0.06
    teo
    0.06
    æŃĩ
    0.06
    éĿĴé¾Ļ
    0.06
    Activations Density 0.302%

    No Known Activations