© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30578
    Prev
    Next
    INDEX
    Explanations

    function calls or variable declarations

    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
    ontos
    -0.08
     ||=
    -0.08
    /dat
    -0.07
    VELO
    -0.07
    IONAL
    -0.07
     Irland
    -0.07
    urgeon
    -0.07
    iae
    -0.07
    è¿Ļæł·çļĦæĥħåĨµ
    -0.07
    yron
    -0.07
    POSITIVE LOGITS
    øk
    0.07
    éĸ¢
    0.06
    å¾ĹäºĨ
    0.06
    è°·
    0.06
    .outputs
    0.06
    æ¼ı
    0.06
    Nation
    0.06
    èĭ¦
    0.06
    次äºİ
    0.06
     pere
    0.06
    Activations Density 0.023%

    No Known Activations