© 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. 30956
    Prev
    Next
    INDEX
    Explanations

    trolley dilemma, utilitarian, Rand

    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
    alias
    -0.08
    ä¸īé«ĺ
    -0.08
    tring
    -0.07
    odr
    -0.07
    phinx
    -0.07
    å¿ĥæĪ¿
    -0.07
    cassert
    -0.07
    odb
    -0.07
    _unused
    -0.07
    èĤĥ
    -0.07
    POSITIVE LOGITS
    åľ¨è¡ĮåĬ¨
    0.08
    èµŀæĪIJ
    0.08
    享ä¹IJ
    0.08
    æĪIJè´¥
    0.07
    å¾Ĺ失
    0.07
    åĬŁåĪ©
    0.07
    æİĴ
    0.07
     felic
    0.07
    æķ´ä½ĵçļĦ
    0.07
    æįŁçĽĬ
    0.07
    Activations Density 0.008%

    No Known Activations