© 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. 45921
    Prev
    Next
    INDEX
    Explanations

    math expressions $y = Ax + B$

    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
    ushi
    -0.07
    ories
    -0.07
    дÑĥм
    -0.07
    zell
    -0.07
    cano
    -0.07
    ibert
    -0.07
    itness
    -0.06
    onitor
    -0.06
    itek
    -0.06
    ali
    -0.06
    POSITIVE LOGITS
    ä¾Ŀ
    0.08
    otten
    0.08
    ỵ
    0.07
    æ³Ħ
    0.07
    æĽ
    0.07
    åĸ±
    0.07
    åij
    0.07
    aré
    0.07
    unas
    0.07
    ä¸įæĦģ
    0.07
    Activations Density 0.003%

    No Known Activations