© 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. 35068
    Prev
    Next
    INDEX
    Explanations

    ";" followed by punctuation or letters

    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
    worth
    -0.08
    å·¨
    -0.08
    asics
    -0.07
    iras
    -0.07
    .setdefault
    -0.07
    ä¸ĸçķĮ级
    -0.07
    误ä¼ļ
    -0.07
    sko
    -0.06
    ister
    -0.06
    誤
    -0.06
    POSITIVE LOGITS
    ;}
    0.08
    ä»Ģ
    0.07
    ;n
    0.06
    饪
    0.06
    ;!
    0.06
    ī
    0.06
    ;y
    0.06
     Setia
    0.06
     unix
    0.06
    uards
    0.06
    Activations Density 0.021%

    No Known Activations