© 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. 61124
    Prev
    Next
    INDEX
    Explanations

    mathematical variables like x, f, g

    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
    bish
    -0.08
    ×Ŀ
    -0.07
    hta
    -0.07
    强çļĦ
    -0.07
    Ŀ
    -0.07
    olik
    -0.07
    UTE
    -0.07
    erez
    -0.07
    ellige
    -0.07
    geh
    -0.06
    POSITIVE LOGITS
    ä¸įåIJĮäºĨ
    0.08
    å®ĥæĺ¯ä¸Ģ个
    0.07
    é©Ĺ
    0.07
    åħ¶äºº
    0.07
    å®ĥå°±æĺ¯
    0.07
    å®ĥæĺ¯ä¸Ģç§į
    0.07
    ()</
    0.07
    .gov
    0.07
    .dtd
    0.07
    .net
    0.06
    Activations Density 0.025%

    No Known Activations