© 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. 11415
    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
    æĺ¥èĬĤæľŁéĹ´
    -0.08
     unga
    -0.07
    hal
    -0.07
    rss
    -0.07
    åºĶæľīå°½æľī
    -0.07
    ambi
    -0.07
    olver
    -0.07
    æīĭæĬĬæīĭ
    -0.07
    åĨįçľĭçľĭ
    -0.07
     nanny
    -0.06
    POSITIVE LOGITS
    丽
    0.08
    arus
    0.07
    ace
    0.07
    æĸ¹å¼ı使çĶ¨
    0.06
    涵
    0.06
    èij©
    0.06
    odium
    0.06
    天æŶ
    0.06
    pear
    0.06
    åľ¨ä¸ĭ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.