© 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. 48702
    Prev
    Next
    INDEX
    Explanations

    sequences

    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
    shire
    -0.09
    ught
    -0.09
    umente
    -0.08
    entifier
    -0.08
    ucker
    -0.08
    zelf
    -0.08
    sek
    -0.08
    jenigen
    -0.08
    éĩij森
    -0.07
    jim
    -0.07
    POSITIVE LOGITS
    ezi
    0.08
    رات
    0.07
    uality
    0.07
    elor
    0.07
    رÙģ
    0.07
    URED
    0.07
    ergestellt
    0.07
    OfWork
    0.07
    ually
    0.07
    人马
    0.07
    Activations Density 0.031%

    No Known Activations