© 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. 51668
    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
    è¿Ļ便æĺ¯
    -0.09
    ä¹ŁçĽ¸å½ĵ
    -0.08
    ä¹ŁæĽ´åĬł
    -0.08
    åı¦ä¸Ģæĸ¹
    -0.08
    mpp
    -0.07
    æĸ¹æīį
    -0.07
    è¿Ľä¸ĢæŃ¥å¼ºåĮĸ
    -0.07
    rados
    -0.07
    TRL
    -0.07
    <![
    -0.07
    POSITIVE LOGITS
    ç¡®å®ŀ
    0.12
    ç¡®å®ŀæĺ¯
    0.11
     indeed
    0.11
    確ãģĭãģ«
    0.10
     effectivement
    0.09
    ç¡®
    0.08
     memang
    0.08
    çļĦç¡®
    0.08
    確實
    0.08
    æľ¬é¢ĺ解éĩĬ
    0.07
    Activations Density 0.000%

    No Known Activations