© 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. 9681
    Prev
    Next
    INDEX
    Explanations

    picked without replacement

    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
    athing
    -0.07
    idah
    -0.07
    Mappings
    -0.07
    elaar
    -0.07
    åĩłæŃ¥
    -0.07
    ÙħÙİا
    -0.07
     recursion
    -0.06
    诡
    -0.06
     Resolution
    -0.06
    央
    -0.06
    POSITIVE LOGITS
     anywhere
    0.10
    æĪĸ以ä¸Ĭ
    0.08
     dentre
    0.08
     ÙħÙĨÙĩÙħ
    0.08
    quisite
    0.07
     elsewhere
    0.07
    åıĸèĩª
    0.07
     Moro
    0.07
    æĪĸå¤ļ
    0.07
    enge
    0.07
    Activations Density 0.019%

    No Known Activations