© 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. 39718
    Prev
    Next
    INDEX
    Explanations

    performing arts, radio station, keyboard macro

    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
    åĨ·åĵ¼
    -0.07
    aidu
    -0.06
     geop
    -0.06
    erate
    -0.06
    peÄį
    -0.06
    воÑİ
    -0.06
    erdade
    -0.06
    «
    -0.06
     Craigslist
    -0.06
    ggia
    -0.06
    POSITIVE LOGITS
    unky
    0.08
    enix
    0.07
    eso
    0.07
    unks
    0.07
    uttle
    0.07
    npos
    0.06
    ANA
    0.06
    arget
    0.06
    æݸ
    0.06
    åŀĥ
    0.06
    Activations Density 0.018%

    No Known Activations