© 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. 18547
    Prev
    Next
    INDEX
    Explanations

    collision, congestion, cramped, clashes

    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
    åĢ¼å¾Ĺä¿¡èµĸ
    -0.08
    æľīæĿ¡ä»¶
    -0.08
    渤
    -0.08
    antina
    -0.08
    erk
    -0.07
    æľīæĿ¡ä»¶çļĦ
    -0.07
    åħ·å¤ĩ
    -0.07
    ä¸Ģ鸣
    -0.07
    é¨Ļ
    -0.07
    åħ·åĤĻ
    -0.07
    POSITIVE LOGITS
    æĭ¥æĮ¤
    0.09
     clash
    0.09
     compression
    0.08
     unavoidable
    0.08
     unsupported
    0.08
     clashes
    0.08
    éĩįåıł
    0.07
    è¢
    0.07
     minimized
    0.07
     avoided
    0.07
    Activations Density 0.006%

    No Known Activations