© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39511
    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
    hers
    -0.07
    º¼
    -0.07
    ä½ĵéĩį
    -0.07
    象山
    -0.07
     mails
    -0.07
    ibold
    -0.07
    ç®Ķ
    -0.07
    æīĭä¸Ń
    -0.07
     Line
    -0.06
    ilder
    -0.06
    POSITIVE LOGITS
    置身äºİ
    0.07
    arily
    0.07
    æŶèĩ³ä»ĬæĹ¥
    0.07
     Globals
    0.07
    è¿Ļä¸ľè¥¿
    0.07
     خصÙĪص
    0.07
    rss
    0.07
    agl
    0.06
    ç´¢æĢ§
    0.06
    å¦ĤæĦı
    0.06
    Activations Density 0.000%

    No Known Activations