© 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. 49931
    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
    èĢ½
    -0.07
     trim
    -0.07
    Ø·ÙĦا
    -0.07
    à¤Ĺà¥Ģ
    -0.07
    abra
    -0.07
    æľīçļĦæĺ¯
    -0.07
    å°±æĺ¯æľī
    -0.07
    çĪ±æĺ¯
    -0.07
    wers
    -0.07
    å¡
    -0.07
    POSITIVE LOGITS
    åįİ强
    0.07
     Neb
    0.07
    个èµŀ
    0.06
    åıĮæĸ¹
    0.06
    æŃ£ç»ı
    0.06
    æĶ¾çŁ¢
    0.06
    alone
    0.06
    uated
    0.06
    è´Ĭ
    0.06
    对æīĭ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.