© 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. 29803
    Prev
    Next
    INDEX
    Explanations

    č followed by Alias or CC

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    åľ¨çº¿çķĻè¨Ģ
    -0.08
    ibur
    -0.08
    åıĤåĬłè¿ĩ
    -0.07
     someday
    -0.07
    ÙİعÙĴ
    -0.07
     Heavenly
    -0.07
    åĬ¨ä¸įåĬ¨
    -0.07
     popr
    -0.07
    æĹ¥æŃ¢
    -0.07
    ÑģÑĤе
    -0.07
    POSITIVE LOGITS
    çĭĤ
    0.09
    åĨį度
    0.08
    éĩįæĸ°
    0.07
    åĨį次
    0.07
    éĩįå¤į
    0.07
    igham
    0.07
     ende
    0.07
    æĸ°çļĦ
    0.06
    éģ½
    0.06
     successful
    0.06
    Activations Density 0.020%

    No Known Activations