© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 6975
    Prev
    Next
    INDEX
    Explanations

    Chinese characters in phrases

    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
    Negative Logits
    baugh
    -0.11
    è¦ģ害
    -0.10
    ELY
    -0.10
    ently
    -0.09
    orgh
    -0.09
    wati
    -0.09
    endale
    -0.09
    jenigen
    -0.09
    avig
    -0.09
    ÑĮÑİ
    -0.09
    POSITIVE LOGITS
    注æĦıçļĦæĺ¯
    0.09
    çī¹åĪ«æ³¨æĦı
    0.09
    åģļçļĦå°±æĺ¯
    0.08
    ech
    0.07
    ful
    0.07
    ä¸įäºĨå¤ļä¹ħ
    0.07
    ev
    0.07
    warzys
    0.07
    itional
    0.07
    ei
    0.06
    Activations Density 0.002%

    No Known Activations