© 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. 28731
    Prev
    Next
    INDEX
    Explanations

    reorder fragments shuffled

    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
    å¼ĢåĪ°
    -0.07
    åıĮ侧
    -0.06
     Nationals
    -0.06
    loaded
    -0.06
    åı¦ä¸Ģè¾¹
    -0.06
    ..."
    -0.06
    åıĮ
    -0.06
    à¹ģà¸ĸว
    -0.06
    лаÑĤ
    -0.06
    åºķçļĦ
    -0.06
    POSITIVE LOGITS
    è¡Ķæİ¥
    0.10
     fragments
    0.09
    Fragment
    0.08
    æĸĩçIJĨ
    0.08
    çīĩ段
    0.08
    æİĴåºı
    0.08
    æī¿æİ¥
    0.08
     shuffled
    0.08
     reorder
    0.08
     fragment
    0.08
    Activations Density 0.003%

    No Known Activations