© 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. 40957
    Prev
    Next
    INDEX
    Explanations

    years 1800s and 1900s

    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¸ĢæľŁ
    -0.07
    ä¸ĢçıŃ
    -0.07
    itech
    -0.07
    apu
    -0.07
    пиÑģа
    -0.07
    æļĤå®ļ
    -0.07
    .utf
    -0.07
    ä¸ĢçĻ¾
    -0.06
    ä¹ĭ士
    -0.06
    缮å®ī
    -0.06
    POSITIVE LOGITS
    =====
    0.07
    eln
    0.07
    ====
    0.07
    elop
    0.07
    jel
    0.07
    abin
    0.07
    æľī趣çļĦæĺ¯
    0.07
    ylan
    0.06
    _collect
    0.06
    ODY
    0.06
    Activations Density 0.349%

    No Known Activations