© 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. 19428
    Prev
    Next
    INDEX
    Explanations

    URL references and numerical answers

    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
     اÙģت
    -0.07
    auge
    -0.07
     conject
    -0.07
    ä¼Ĺ人
    -0.07
    otar
    -0.07
    å°½äºĨ
    -0.06
    ä¸Ŀ带
    -0.06
     vắt
    -0.06
    ARENT
    -0.06
    rand
    -0.06
    POSITIVE LOGITS
    åĭĴæĸ¯
    0.08
    holm
    0.08
    Ñĥл
    0.07
    лиÑĨа
    0.07
    ertest
    0.07
     ulo
    0.07
     getr
    0.07
    опо
    0.07
    spur
    0.07
    etails
    0.06
    Activations Density 0.001%

    No Known Activations