© 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. 39403
    Prev
    Next
    INDEX
    Explanations

    ascending order, units digit of

    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
    çĬ¯ç½ªäºĭå®ŀ
    -0.07
     Trinh
    -0.07
    ابÙĤ
    -0.07
    ).__
    -0.06
    OUNDS
    -0.06
    ä»ĵ
    -0.06
    éģĵ人
    -0.06
    æĦ¿æĦı
    -0.06
    rial
    -0.06
    ختÙĩ
    -0.06
    POSITIVE LOGITS
    çŃĶé¢ĺ
    0.09
     Sach
    0.08
    æŃ£ç¡®çļĦæĺ¯
    0.08
     Least
    0.08
    vall
    0.07
     misk
    0.07
    åįķ项éĢīæĭ©é¢ĺ
    0.07
    æŃ£ç¡®çļĦ
    0.07
    اة
    0.07
    elerde
    0.07
    Activations Density 0.106%

    No Known Activations