© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17097
    Prev
    Next
    INDEX
    Explanations

    Sub-Saharan Africa countries

    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
     appunto
    -0.09
    ofday
    -0.09
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.09
    à¸Ĭีà¸ŀ
    -0.08
    æ¯ıæĹ¥ä¸Ģ
    -0.08
    æĢİä¹ĪåĬŀåij¢
    -0.07
    ä¹Łæľīä¸Ģå®ļçļĦ
    -0.07
    AnimationFrame
    -0.07
    æĪĸèĢħ说
    -0.07
    临åºĬç»ıéªĮ
    -0.07
    POSITIVE LOGITS
     vs
    0.08
    ab
    0.07
    ung
    0.06
     Wik
    0.06
    .ab
    0.06
    河水
    0.06
    thal
    0.06
    横
    0.06
    仲
    0.06
    æĥħåĨµè¯´æĺİ
    0.06
    Activations Density 0.001%

    No Known Activations