© 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. 52044
    Prev
    Next
    INDEX
    Explanations

    mathematical constants, code, and license

    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
    ImageContext
    -0.07
    ç«ĭæĸ°
    -0.07
    ä½ĵèĤ²æĢ»å±Ģ
    -0.07
    SetColor
    -0.07
    æ¯ıä¸Ģ个ç»ĨèĬĤ
    -0.07
     Boo
    -0.07
    å¸ĪçĶŁçļĦ
    -0.07
    é²²
    -0.06
     itself
    -0.06
    hud
    -0.06
    POSITIVE LOGITS
    istr
    0.07
    lash
    0.07
    isodes
    0.06
    toff
    0.06
    cales
    0.06
    Ñģев
    0.06
    ilas
    0.06
    irth
    0.06
    orda
    0.06
    cum
    0.06
    Activations Density 0.008%

    No Known Activations