© 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. 45570
    Prev
    Next
    INDEX
    Explanations

    mathematical/code structure markers

    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
    <decltype
    -0.07
    es
    -0.07
    æģª
    -0.06
    ibas
    -0.06
    oom
    -0.06
    ç¹ŀ
    -0.06
    λλ
    -0.06
    çļĦå°ıäºĭ
    -0.06
    uur
    -0.06
    ä»ĸåij½
    -0.06
    POSITIVE LOGITS
    æħ°
    0.08
    ứt
    0.08
    cule
    0.07
    olumn
    0.07
    볤
    0.07
    ilder
    0.07
    _Release
    0.07
    zez
    0.07
    çİĭå®ī
    0.07
    ersp
    0.07
    Activations Density 0.002%

    No Known Activations