© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17224
    Prev
    Next
    INDEX
    Explanations

    legal judgment or decree

    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
    _DEFINED
    -0.08
    éļĪ
    -0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    -0.07
    ayu
    -0.07
    _defined
    -0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯
    -0.07
    æĬķæłĩæĸĩ件éĢĴ交
    -0.07
    outh
    -0.07
    atical
    -0.07
    _cpp
    -0.07
    POSITIVE LOGITS
    ç»ĵæŀľ
    0.10
    ç»ĵæŀľçļĦ
    0.10
     final
    0.09
    çĶŁæķĪåIJİ
    0.09
     result
    0.09
    ç»ĵæŀľæĺ¯
    0.08
     decisions
    0.08
    final
    0.08
     outcome
    0.08
     resultat
    0.08
    Activations Density 0.196%

    No Known Activations