© 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. 21172
    Prev
    Next
    INDEX
    Explanations

    programming test classes

    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
    ä¸Ģåıij
    -0.08
    åı¥è¯Ŀ说
    -0.07
    immä
    -0.07
    ä¸Ĭ交
    -0.07
     somewhere
    -0.07
     whichever
    -0.07
    OTE
    -0.07
    å°±æĺ¯è¿Ļæł·
    -0.07
    neau
    -0.07
     sela
    -0.06
    POSITIVE LOGITS
    atih
    0.08
    wab
    0.07
    oji
    0.07
     Gins
    0.07
    ä¸ĥä¸ĥ
    0.07
    åħµçİĭ
    0.07
    dor
    0.07
     Worldwide
    0.07
    Äĵt
    0.07
    habi
    0.07
    Activations Density 0.186%

    No Known Activations