© 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. 11283
    Prev
    Next
    INDEX
    Explanations

    left and right indicators

    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
    ä¸ŃéĹ´çļĦ
    -0.11
    ä¸ŃéĹ´
    -0.10
    ä¸Ĭä¸ĭ
    -0.09
    åīįåIJİ
    -0.09
     intermediary
    -0.09
    åįĹåĮĹ
    -0.08
     intermediate
    -0.08
    ä¸Ńä»ĭ
    -0.08
    两端
    -0.08
     balanced
    -0.08
    POSITIVE LOGITS
    åįĬè¾¹
    0.10
    ä¸Ģ侧
    0.09
     unilateral
    0.09
    åIJijåı³
    0.09
    åįķè¾¹
    0.08
    åįķæĸ¹éĿ¢
    0.08
    åįķåIJij
    0.08
    é£İ顺
    0.08
    è¿Ļè¾¹çļĦ
    0.08
    åIJijåIJİ
    0.08
    Activations Density 0.161%

    No Known Activations