© 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. 23750
    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
    iker
    -0.08
    ¿
    -0.07
    inga
    -0.07
    perk
    -0.07
     Bhar
    -0.07
    anges
    -0.07
    éļıæŶ
    -0.06
    æĵįå®Ī
    -0.06
    è¿İåIJĪ
    -0.06
    ikers
    -0.06
    POSITIVE LOGITS
    è´¨éĩı好
    0.07
    stown
    0.07
    ä¸įè§ģ
    0.07
    æ²Ĥ
    0.07
    å°ıåħĶ
    0.07
    .consume
    0.07
    rial
    0.06
    HandlerContext
    0.06
     Dien
    0.06
    ä¸Ńå¿ĥåĮ»éĻ¢
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.