© 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. 22566
    Prev
    Next
    INDEX
    Explanations

    numbers in lists

    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
    èĮ¨
    -0.07
    ä¸Ģ
    -0.06
    prech
    -0.06
    ä¸ĢæĦ£
    -0.06
    elts
    -0.06
    жаÑİ
    -0.06
    幽幽
    -0.06
     Refugee
    -0.06
    uera
    -0.06
    éļı
    -0.06
    POSITIVE LOGITS
    atables
    0.08
    aum
    0.08
    天ä¹ĭ
    0.08
    aida
    0.08
     подÑĢÑĥ
    0.07
    [test
    0.07
     Afinal
    0.07
    emming
    0.07
    ÏĥÏĦή
    0.07
    aN
    0.07
    Activations Density 0.001%

    No Known Activations