© 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. 10399
    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
    implicit
    -0.07
    צ׾
    -0.06
    æ·¼
    -0.06
    isar
    -0.06
    ia
    -0.06
     unders
    -0.06
    渡è¿ĩ
    -0.06
     implicit
    -0.06
    urnished
    -0.06
    ynch
    -0.06
    POSITIVE LOGITS
    ykl
    0.07
    à¸Ľà¸£à¸°à¸Ĭ
    0.07
    è¹Ī
    0.07
     Barros
    0.07
    å·¥ä½ľéľĢè¦ģ
    0.07
    лко
    0.07
    æ³¾
    0.06
    ORY
    0.06
    çĽ¸ä¿¡æĪij
    0.06
    ç½
    0.06
    Activations Density 0.000%

    No Known Activations