© 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. 38859
    Prev
    Next
    INDEX
    Explanations

    topology, order, product

    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
    åģ¿
    -0.08
    iliz
    -0.08
    积æŀģç»Ħç»ĩ
    -0.07
     klo
    -0.07
     captive
    -0.07
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.07
    æĿ
    -0.07
    æī¬éķ¿
    -0.07
    /master
    -0.07
     Wen
    -0.07
    POSITIVE LOGITS
     inherited
    0.08
    _backend
    0.07
    olino
    0.07
    .define
    0.07
    fld
    0.07
    herited
    0.07
    zer
    0.07
    ove
    0.07
    osp
    0.07
    WARE
    0.07
    Activations Density 0.033%

    No Known Activations