© 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. 33217
    Prev
    Next
    INDEX
    Explanations

    list-depth, span, go

    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
    åĴķ
    -0.08
    обе
    -0.06
    istik
    -0.06
    usser
    -0.06
    held
    -0.06
    ame
    -0.06
     opini
    -0.06
    auen
    -0.06
    informatics
    -0.06
    ynos
    -0.06
    POSITIVE LOGITS
    _generated
    0.08
    weiler
    0.08
    _place
    0.07
    æİ¥æĽ¿
    0.07
    zar
    0.07
    ä½Ķ
    0.07
    åĮħä½ı
    0.07
    loader
    0.07
    æĸ¯é¡¿
    0.07
     ës
    0.07
    Activations Density 0.007%

    No Known Activations