© 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. 52051
    Prev
    Next
    INDEX
    Explanations

    New Zealand

    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
    नाव
    -0.07
    jik
    -0.06
    é¦ģ
    -0.06
    è¯·çĽ´æİ¥
    -0.06
    åľ¨ä¼ļä¸Ĭ
    -0.06
    åĨħ设
    -0.06
    뢰
    -0.06
     "{$
    -0.06
    arded
    -0.06
    ihar
    -0.06
    POSITIVE LOGITS
    èº«åľ¨
    0.09
    置身
    0.09
    oya
    0.08
    çİ°å®ŀæĦıä¹ī
    0.08
    çİ°å®ŀçĶŁæ´»ä¸Ń
    0.08
    社ä¼ļå®ŀè·µ
    0.08
    olla
    0.08
    çİ°å®ŀä¸Ń
    0.07
    ä¸İçİ°å®ŀ
    0.07
    身å¤Ħ
    0.07
    Activations Density 0.673%

    No Known Activations