© 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. 16015
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames or titles

    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
    ymar
    -0.07
     Leban
    -0.07
    Ĺı
    -0.07
    гин
    -0.07
    åĸľæĢĴ
    -0.07
     Bashar
    -0.07
    è§ģå¾Ĺ
    -0.07
    身çļĦ
    -0.07
    pluck
    -0.06
    ided
    -0.06
    POSITIVE LOGITS
     Fucking
    0.10
    cue
    0.07
    建设æĪIJ为
    0.07
    agra
    0.07
    owell
    0.06
     fucking
    0.06
    upp
    0.06
     Départ
    0.06
    åįİè¯Ń
    0.06
     Tattoo
    0.06
    Activations Density 1.193%

    No Known Activations