© 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. 9536
    Prev
    Next
    INDEX
    Explanations

    linear operators and mathematical predicates

    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
    å¾Ĺ天
    -0.08
    åIJ¸çĿĽ
    -0.07
    èĬ¹
    -0.07
    èĬĿ麻
    -0.07
    æĿ¥èĩªç½ij绾
    -0.07
    ä¹Łä¸įæķ¢
    -0.07
    abo
    -0.07
    ä¸įä»ħéľĢè¦ģ
    -0.07
    顾åIJįæĢĿ
    -0.07
    ä½
    -0.07
    POSITIVE LOGITS
     underlying
    0.11
    åıªä¸įè¿ĩ
    0.10
    æľ¬è´¨ä¸Ĭ
    0.10
     underneath
    0.09
     originally
    0.09
    åıªä¸įè¿ĩæĺ¯
    0.09
    æľ¬è´¨
    0.08
     Originally
    0.08
     inherently
    0.08
    åıªä¸įéģİ
    0.08
    Activations Density 0.257%

    No Known Activations