© 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. 4567
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Renzi
    -0.07
    eluk
    -0.07
    .defer
    -0.07
    ëĶ
    -0.07
    .ibm
    -0.07
    InParameter
    -0.07
     sánh
    -0.07
    .Args
    -0.07
    ç¦ıçĶ°
    -0.07
    uos
    -0.07
    POSITIVE LOGITS
    å¾Ĺä¸į
    0.07
    akh
    0.07
    æµģè¨Ģ
    0.07
    eya
    0.06
    agh
    0.06
    orest
    0.06
    agal
    0.06
    ç»ıåħ¸çļĦ
    0.06
    aga
    0.06
    产åĵģåĪĨç±»
    0.06
    Activations Density 0.000%

    No Known Activations