© 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. 27525
    Prev
    Next
    INDEX
    Explanations

    urls starting with http or https

    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
    æľ¬ä¹¦
    -0.08
    ·
    -0.07
    æľ¬æĽ¸
    -0.07
    iega
    -0.06
    étique
    -0.06
    olicit
    -0.06
    并åı¯
    -0.06
    ä¸įäºĨäºĨ
    -0.06
    &apos
    -0.06
    ekyll
    -0.06
    POSITIVE LOGITS
    اÙĨا
    0.08
    .*(
    0.07
     Viên
    0.07
    éĩĮéĿ¢æľī
    0.07
     vaguely
    0.07
    裡éĿ¢
    0.07
    讲çļĦæĺ¯
    0.06
     esp
    0.06
    ãģĿãģĵ
    0.06
    oya
    0.06
    Activations Density 0.552%

    No Known Activations