© 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. 34333
    Prev
    Next
    INDEX
    Explanations

    legally or technically wrongful

    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
    bol
    -0.08
    ä¸ĢçĶŁä¸Ń
    -0.08
    ussen
    -0.08
    Bol
    -0.07
    áĥ¯
    -0.07
    idine
    -0.07
    olib
    -0.07
    idere
    -0.07
    ÙĪاÙħ
    -0.07
    undef
    -0.07
    POSITIVE LOGITS
    æķħæĦı
    0.08
    æīĢè¨Ģ
    0.08
     deliberately
    0.07
     terecht
    0.07
     unfairly
    0.07
     contradict
    0.07
    æīĢ说çļĦ
    0.07
     wisely
    0.07
     should
    0.07
     wrongly
    0.07
    Activations Density 0.048%

    No Known Activations