© 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. 15880
    Prev
    Next
    INDEX
    Explanations

    function calls and program execution

    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
     Minh
    -0.06
    ìĨ
    -0.06
    éĢłå°±
    -0.06
    島ãģ®
    -0.06
    inou
    -0.06
    YTE
    -0.06
    åIJį
    -0.06
    島
    -0.06
    ellet
    -0.06
    éĩįè¦ģçļĦäºĭæĥħ
    -0.06
    POSITIVE LOGITS
    åIJĮå¿Ĺ为
    0.08
    enticator
    0.08
    eningen
    0.07
    工信
    0.07
    Ĵ·
    0.07
    μμ
    0.07
    enticate
    0.07
    uracy
    0.07
    ettura
    0.07
     vist
    0.07
    Activations Density 0.037%

    No Known Activations