© 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. 34661
    Prev
    Next
    INDEX
    Explanations

    explains "means" or "meaning"

    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¦Ĵ
    -0.07
    ä¸Ģç»ıåıijçİ°
    -0.07
    çļĦ身影
    -0.07
    æĩ
    -0.07
    Ïģν
    -0.07
    æĪijåĽ½ç»ıæµİ
    -0.07
    à¹Ģà¸ģร
    -0.07
    æĨĶ
    -0.07
    &W
    -0.07
    &P
    -0.07
    POSITIVE LOGITS
    æĦı为
    0.09
    å¯ĵæĦı
    0.09
    å¼ķçĶ³
    0.08
    æĭīä¸ģ
    0.08
     literally
    0.08
     ëľ»
    0.07
    lah
    0.07
     meaning
    0.07
    çļĦæĦıæĢĿæĺ¯
    0.07
    åIJ«ä¹ī
    0.07
    Activations Density 0.068%

    No Known Activations