© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2257
    Prev
    Next
    INDEX
    Explanations

    Asian American demographics or culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    bes
    -0.28
     sheer
    -0.25
    è¡·
    -0.24
    ä¹¾åĿ¤
    -0.23
     Hispan
    -0.23
    ease
    -0.22
    æįº
    -0.22
    bial
    -0.21
    gne
    -0.21
    è¿Ļ款
    -0.21
    POSITIVE LOGITS
     Taiwanese
    0.26
    олов
    0.24
    ApiResponse
    0.24
    åľ¨æĹ¥æľ¬
    0.23
     Lowe
    0.23
    çĮĹ
    0.23
    (es
    0.22
     Xia
    0.22
     GMO
    0.22
    ç±»åŀĭçļĦ
    0.22
    Activations Density 0.009%

    No Known Activations