© 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. 10818
    Prev
    Next
    INDEX
    Explanations

    Turkey

    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
     поÑĥ
    -0.08
    tric
    -0.08
    çİĭç»´
    -0.08
    eking
    -0.08
     VÅ¡
    -0.08
    äär
    -0.08
    æk
    -0.08
    é«ĺå¯Ĩ
    -0.08
    æºIJ
    -0.08
    itse
    -0.08
    POSITIVE LOGITS
     Ankara
    0.10
     Istanbul
    0.09
    åľŁèĢ³åħ¶
    0.08
     Turkish
    0.08
     Türkiye
    0.08
     Anadolu
    0.08
     Antalya
    0.07
     Ãĩ
    0.07
     Turkey
    0.07
    ãĥĪãĥ«
    0.07
    Activations Density 0.333%

    No Known Activations