© 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. 56370
    Prev
    Next
    INDEX
    Explanations

    more likely, better option

    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
    æĹ¢åı¯ä»¥
    -0.08
    度
    -0.08
    ptest
    -0.07
    æĹ¢æĺ¯
    -0.07
     Degree
    -0.07
    ubre
    -0.07
    ä¸įèĥ½å¤Ł
    -0.07
    ç§Ģæīį
    -0.07
    ibur
    -0.07
    æĮij
    -0.07
    POSITIVE LOGITS
    çļĦæĺ¯
    0.12
     than
    0.11
    -than
    0.10
    than
    0.09
     ÙĪØ£Ùĥثر
    0.09
    Than
    0.09
    çļĦæĺ¯ä¸Ģ个
    0.09
     Than
    0.09
     niż
    0.09
     بÙĥØ«ÙĬر
    0.09
    Activations Density 0.033%

    No Known Activations