© 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. 51589
    Prev
    Next
    INDEX
    Explanations

    demonstrative following "that"

    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
    è¿Ļæł·ä¸Ģ个
    -0.09
    æł¹æľ¬å°±ä¸į
    -0.09
    æł¹æľ¬ä¸į
    -0.09
     Merke
    -0.08
    è¿Ļæł·åŃIJ
    -0.08
    è¡·å¿ĥçļĦ
    -0.08
    Įĵ
    -0.08
    æł¹æľ¬æ²¡æľī
    -0.08
    æķħæѤ
    -0.08
    æķħèĢĮ
    -0.08
    POSITIVE LOGITS
    //@
    0.06
    ä¹Łè¢«
    0.06
    çĶ
    0.06
     ÑĤоже
    0.06
    ž
    0.06
    çıį
    0.06
    æĻļ
    0.05
    å¢ŀ
    0.05
    åįł
    0.05
     باÙĦÙħÙĨ
    0.05
    Activations Density 0.096%

    No Known Activations