© 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. 34554
    Prev
    Next
    INDEX
    Explanations

    multiplied and Chinese characters

    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
    ä¸įæİĴéĻ¤
    -0.08
    ä¸ĭåIJĮ
    -0.08
    ä¸Ģ路走æĿ¥
    -0.08
    éraux
    -0.08
    åĪ©äºİ
    -0.08
     whereby
    -0.08
    çļĦæĦıæĢĿæĺ¯
    -0.07
    αιο
    -0.07
    /--
    -0.07
    åŃĹ
    -0.07
    POSITIVE LOGITS
    æĺ¯å¤ļå°ij
    0.10
    æı©
    0.08
    è®°
    0.07
    è¿Ļä¸ĢéĹ®é¢ĺ
    0.07
    æĵ¦å¹²
    0.07
     den
    0.07
    åļ¼
    0.07
     multiplied
    0.07
     fres
    0.07
    åŀ£
    0.07
    Activations Density 0.040%

    No Known Activations