© 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. 16975
    Prev
    Next
    INDEX
    Explanations

    Lithuania and Latvian related terms

    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
    太è¡Į
    -0.08
     Detroit
    -0.08
    çĦ¦ä½ľ
    -0.08
    墨西åĵ¥
    -0.07
    çľ¼åľĪ
    -0.07
    JNI
    -0.07
    gern
    -0.07
     جراÙħ
    -0.07
     طبÙĤ
    -0.07
     Mexican
    -0.07
    POSITIVE LOGITS
     Eston
    0.09
     Latv
    0.08
     Armenian
    0.08
     Estonia
    0.08
     Moldova
    0.07
     Latvia
    0.07
    inh
    0.07
    æĻĵå¾Ĺ
    0.07
    ä¿IJ
    0.07
    çīł
    0.07
    Activations Density 0.102%

    No Known Activations