© 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. 59903
    Prev
    Next
    INDEX
    Explanations

    always been or had

    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
    缴æİ¥å°Ĩ
    -0.10
    ç´¢æĢ§
    -0.09
    ook
    -0.09
    缴æİ¥ä»İ
    -0.09
    缴æİ¥æĬĬ
    -0.09
    æŃ£å¥½
    -0.08
    ä¹Łçº·çº·
    -0.08
    缮åīįå·²ç»ı
    -0.08
    adak
    -0.08
    ä»ĸ羣çļĦ
    -0.08
    POSITIVE LOGITS
     تÙĤرÙĬب
    0.13
    以æĿ¥çļĦ
    0.12
    å§ĭèĩ³ç»Ī
    0.11
    以ä¾Ĩ
    0.11
    ä¿ĿæĮģçĿĢ
    0.10
    ä¸Ģ缴æĺ¯
    0.09
    å§ĭç»Ī
    0.09
    以æĿ¥
    0.09
     except
    0.08
    ä¸Ģ缴éĥ½æĺ¯
    0.08
    Activations Density 0.209%

    No Known Activations