© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19743
    Prev
    Next
    INDEX
    Explanations

    Turkey and Turkish places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shiv
    -0.09
    lá
    -0.09
    оÑģÑĤ
    -0.09
    ç©Ĺ
    -0.09
    é£İæ³¢
    -0.08
    澳大
    -0.08
    åīĬ
    -0.08
    大åݦ
    -0.08
    Echo
    -0.08
    bris
    -0.08
    POSITIVE LOGITS
    åľŁèĢ³åħ¶
    0.14
     Turkey
    0.12
     Turkish
    0.12
     Atatürk
    0.11
     ТÑĥÑĢ
    0.11
    Turkey
    0.11
     Ankara
    0.10
     Istanbul
    0.10
     Ottoman
    0.10
     Turks
    0.09
    Activations Density 0.050%

    No Known Activations