© 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. 62962
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĶ¶èĹıæľ¬ç«Ļ
    -0.09
    ÃŃss
    -0.08
    çIJħ
    -0.08
    steen
    -0.08
    Mocks
    -0.08
    ÃŃž
    -0.08
    .tech
    -0.08
    мов
    -0.08
    ảm
    -0.08
    ÏĮδ
    -0.08
    POSITIVE LOGITS
    èĻ±
    0.07
    æĥ¨
    0.06
    åĸľæĢĴ
    0.06
    azu
    0.06
     pros
    0.06
    äºĮ代
    0.06
    /init
    0.05
    kena
    0.05
    asio
    0.05
    _cor
    0.05
    Activations Density 0.000%

    No Known Activations