© 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. 34327
    Prev
    Next
    INDEX
    Explanations

    chemical or place names

    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
    å¦Ĥæ°´
    -0.08
    arla
    -0.07
    åIJĦæĸ¹éĿ¢çļĦ
    -0.07
    à¸ĵี
    -0.07
    ä¸įæ¼ı
    -0.06
    åIJĦ项活åĬ¨
    -0.06
    æĢ¯
    -0.06
    åIJĦç§ij室
    -0.06
    碧
    -0.06
     Customize
    -0.06
    POSITIVE LOGITS
     themselves
    0.10
    éĢĻäºĽ
    0.10
    è¿ĻäºĽ
    0.10
    ä¸Ģç±»
    0.10
    è¿Ļç±»
    0.09
    å®ĥ们æĺ¯
    0.09
    以åıĬä¸ĢäºĽ
    0.09
    以åıĬåħ¶ä»ĸ
    0.09
    以åıĬåIJĦç§į
    0.09
    è¿ĻäºĽå°ı
    0.09
    Activations Density 0.308%

    No Known Activations