© 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. 28200
    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
    以åıĬä¸ĢäºĽ
    -0.10
    æĪĸèĢħæĺ¯
    -0.08
    ä¸ĬéĿ¢
    -0.08
    è¿ĺæľīä¸ĢäºĽ
    -0.08
    以åıĬåIJĦç§į
    -0.08
    èĢĮä¸Ķ
    -0.08
    çļĦéĤ£äºĽ
    -0.08
    âĢ¦.
    -0.08
    åĴĮä¸ĢäºĽ
    -0.08
     ÑģобÑģÑĤвенно
    -0.08
    POSITIVE LOGITS
     via
    0.09
    æŶéľĢ
    0.08
    via
    0.07
    ään
    0.07
    为æİ¨è¿Ľ
    0.07
    lis
    0.07
     vs
    0.07
    Ùĥب
    0.06
    å¦ĤéľĢ
    0.06
    为éģ¿åħį
    0.06
    Activations Density 0.000%

    No Known Activations