© 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. 18803
    Prev
    Next
    INDEX
    Explanations

    coding region or sequence

    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
    è¶ħè½½
    -0.07
    åħį费注åĨĮ
    -0.07
    brands
    -0.07
    天ä¸ĭ第ä¸Ģ
    -0.07
    ç»ĵ交
    -0.06
    樽
    -0.06
    ipl
    -0.06
    è¡¡
    -0.06
    æĬĬåŃ¦ä¹ł
    -0.06
    æĸ¹ãģ®
    -0.06
    POSITIVE LOGITS
    æĺ¯ä¸Ģ段
    0.08
    onan
    0.07
    çļĦä¸Ģ段
    0.07
    Mã
    0.07
     interrupted
    0.07
    段çļĦ
    0.07
    åħ¨éķ¿
    0.07
    ä¸Ģ段
    0.07
    äºĨä¸Ģ段
    0.07
     Sardegna
    0.07
    Activations Density 0.062%

    No Known Activations