© 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. 38416
    Prev
    Next
    INDEX
    Explanations

    selection and preference

    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
    人æĦı
    -0.08
     ÏĢεÏģιÏĥÏĥÏĮÏĦε
    -0.07
     Gon
    -0.07
    elus
    -0.07
    éĸij
    -0.07
    endance
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    äºĽä»Ģä¹Ī
    -0.07
    ackets
    -0.07
    ä¸įå°ij
    -0.06
    POSITIVE LOGITS
    为æŃ¢
    0.07
    æıIJé«ĺåѦçĶŁ
    0.07
    æĻĵ
    0.07
    æĪĸæľī
    0.07
    æĺ¯åĵª
    0.06
    ай
    0.06
    æıIJé«ĺåѦçĶŁçļĦ
    0.06
    æĬ¥åIJįæŶ
    0.06
    è¿Ļ对äºİ
    0.06
     /^(
    0.06
    Activations Density 0.007%

    No Known Activations