© 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. 37455
    Prev
    Next
    INDEX
    Explanations

    listing items

    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
    ë²Į
    -0.08
     Ketiga
    -0.07
    .lt
    -0.07
    ulut
    -0.07
    utor
    -0.07
     Wenger
    -0.07
    velle
    -0.07
    inger
    -0.07
    kunde
    -0.07
    ambu
    -0.07
    POSITIVE LOGITS
    åı¦ä¸Ģ个
    0.09
    åı¦ä¸Ģæĸ¹éĿ¢
    0.09
    åı¦å¤ĸä¸Ģ个
    0.08
    èĩ³äºİ
    0.08
    åı¦ä¸Ģ
    0.08
    åı¦ä¸ĢåĢĭ
    0.08
    åı¦
    0.08
     respectiv
    0.08
     another
    0.08
    ois
    0.07
    Activations Density 0.328%

    No Known Activations