© 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. 13613
    Prev
    Next
    INDEX
    Explanations

    degree of property

    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
    ambil
    -0.08
    好å¤ĦçļĦ
    -0.07
    ä¸įäºĨçļĦ
    -0.07
    attrs
    -0.07
     sekaligus
    -0.07
    åĴĮç¾İ
    -0.07
    åĺĽ
    -0.07
     Zwecke
    -0.07
    åĴĮæıIJé«ĺ
    -0.07
    اÙĦب
    -0.07
    POSITIVE LOGITS
    æĺ¯åIJ¦æľī
    0.14
    æľī没æľī
    0.13
    æĺ¯åIJ¦
    0.13
     whether
    0.13
    whether
    0.13
    æĺ¯åIJ¦ä¸º
    0.13
    æĺ¯åIJ¦åħ·æľī
    0.13
    æĺ¯åIJ¦ä¸İ
    0.13
    Whether
    0.13
    æĺ¯åIJ¦åľ¨
    0.13
    Activations Density 0.100%

    No Known Activations