© 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. 59870
    Prev
    Next
    INDEX
    Explanations

    known as

    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
    ç³ľ
    -0.07
     /^[
    -0.07
    orti
    -0.06
    设æ³ķ
    -0.06
    èĢ½
    -0.06
    upi
    -0.06
    ç»ı
    -0.06
    rees
    -0.06
     vole
    -0.06
    ored
    -0.06
    POSITIVE LOGITS
    ä¿Ĺ称
    0.21
    被称为
    0.19
    ä¹Łè¢«ç§°ä¸º
    0.16
    被èªī为
    0.15
     (“
    0.15
     ("
    0.15
    åıĪ称为
    0.14
     tzw
    0.14
    åıĪ称
    0.14
     nicknamed
    0.14
    Activations Density 0.518%

    No Known Activations