© 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. 15477
    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
     Kraft
    -0.07
    çļĦåĵģç§į
    -0.06
     \/
    -0.06
    æĸ°çļĦæĮijæĪĺ
    -0.06
    etta
    -0.06
    ern
    -0.06
    axes
    -0.06
    èĤĦ
    -0.06
     <<<
    -0.06
    é»į
    -0.05
    POSITIVE LOGITS
    åĸ¶
    0.09
    argout
    0.08
    åķĨ
    0.08
     gesta
    0.08
     giù
    0.08
    jsonp
    0.08
    byname
    0.08
    cae
    0.07
    ysten
    0.07
    út
    0.07
    Activations Density 0.000%

    No Known Activations