© 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. 42524
    Prev
    Next
    INDEX
    Explanations

    unsafe programming keywords

    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
    ame
    -0.09
    {/*
    -0.08
    £
    -0.08
    uguay
    -0.08
    outine
    -0.08
    ť
    -0.08
    antan
    -0.08
    è°¢
    -0.08
    wyn
    -0.08
    {//
    -0.07
    POSITIVE LOGITS
    illet
    0.07
    uis
    0.06
    æľīå¿ĥ人
    0.06
    åĮĻ
    0.06
    epam
    0.06
    ä¸įå®ĮçļĦ
    0.06
    0.06
    ayet
    0.06
    éĪķ
    0.06
    å±ħåīį
    0.05
    Activations Density 0.188%

    No Known Activations