© 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. 9856
    Prev
    Next
    INDEX
    Explanations

    financial, names, supply, online, site

    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
     inoltre
    -0.09
    meli
    -0.09
     btw
    -0.08
    ä½Ĩçİ°åľ¨
    -0.08
    综ä¸Ĭ
    -0.08
    vs
    -0.08
     übrigens
    -0.08
    alda
    -0.08
    æī©å±ķèµĦæĸĻ
    -0.08
     thankfully
    -0.08
    POSITIVE LOGITS
    ä¹Łå°±æĺ¯è¯´
    0.11
    æį¢åı¥è¯Ŀ说
    0.09
    —that
    0.08
     sogenannten
    0.08
    è¿Ļ便æĺ¯
    0.08
    ä¹Łå°±æĺ¯
    0.08
     ÙĪØ°ÙĦÙĥ
    0.08
    ãģĦãĤıãĤĨãĤĭ
    0.08
    .
    0.08
    å½¢æĪIJäºĨä¸Ģ个
    0.08
    Activations Density 0.199%

    No Known Activations