© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62226
    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
    .intent
    -0.08
    åħį费注åĨĮ
    -0.08
     Brows
    -0.08
    çļĦå·¥ä½ľç»ıéªĮ
    -0.08
    enson
    -0.08
    OfWork
    -0.07
    ÏĢί
    -0.07
    leases
    -0.07
    天çĽĸ
    -0.07
     ÙĬد
    -0.07
    POSITIVE LOGITS
    åĩºä¸į
    0.07
    ç²¾ç¾İ
    0.06
     ÙĬعÙĨÙĬ
    0.06
    avatar
    0.06
    aign
    0.06
    å±±å¸Ĥ
    0.06
    r
    0.06
    onom
    0.06
    onde
    0.06
     Era
    0.06
    Activations Density 0.000%

    No Known Activations