© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9317
    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
    ä¸ĭåIJĮ
    -0.07
    igham
    -0.07
    l
    -0.07
    ju
    -0.07
    rim
    -0.06
    lvl
    -0.06
    заÑĢа
    -0.06
    £
    -0.06
    å¾Īå¥ĩæĢª
    -0.06
     lvl
    -0.06
    POSITIVE LOGITS
    禧
    0.08
    plet
    0.08
    initi
    0.08
    odik
    0.07
    æĸĩçIJĨ
    0.07
    egan
    0.07
    niec
    0.07
    гелÑĮ
    0.07
    lopedia
    0.07
    pong
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.