© 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. 45868
    Prev
    Next
    INDEX
    Explanations

    records with geographic regions

    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åijĺ对
    -0.07
    ÄįástÃŃ
    -0.07
     tellement
    -0.07
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.07
    ussi
    -0.06
    åľ°çIJĨä½įç½®ä¼ĺè¶Ĭ
    -0.06
    çļĦæĸ¹æ³ķæĿ¥
    -0.06
    ä¼ģä¸ļ对
    -0.06
    SectionsIn
    -0.06
    产åĵģåľ¨
    -0.06
    POSITIVE LOGITS
     appunto
    0.09
     otherwise
    0.08
    æĺ¯åħ¶
    0.08
    ä¹ħä¹ĭ
    0.08
    å½ĵçĦ¶äºĨ
    0.07
    为åħ¶
    0.07
    ç»Ļä»ĸ们
    0.07
     pourtant
    0.07
     иÑħ
    0.07
    their
    0.06
    Activations Density 2.455%

    No Known Activations