© 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. 20096
    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
    à¦ĺ
    -0.08
     redesigned
    -0.08
    éĢģä½ł
    -0.08
    ä¹Łä¸įä¸Ģå®ļ
    -0.08
    etsk
    -0.08
    æľīçĤ¹åĥı
    -0.08
    onda
    -0.08
    ibri
    -0.08
    è´¢ç»ı大åѦ
    -0.08
     finally
    -0.08
    POSITIVE LOGITS
    âĢIJ
    0.08
    ɵ
    0.06
    æĦıåij³
    0.06
    çĨł
    0.06
     contr
    0.06
    åIJĪåIJĮå±¥è¡Į
    0.06
    ation
    0.06
    zcze
    0.06
    èľ¡
    0.06
    วà¹Īามี
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.