© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16505
    Prev
    Next
    INDEX
    Explanations

    names of people with East Asian or German origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ç¾½
    -0.20
    ull
    -0.20
    åįģäºĮäºĶ
    -0.18
    çŁ¾
    -0.17
    argo
    -0.17
    åīľ
    -0.17
    æ¼ı
    -0.17
     reduced
    -0.16
    éģ®
    -0.16
    ikit
    -0.16
    POSITIVE LOGITS
    ä¹Łå¥½
    0.20
    æī³
    0.20
    /ph
    0.18
    çķħ
    0.18
    _Osc
    0.18
    =(↵
    0.18
    _("
    0.18
    usercontent
    0.18
    åĭĻ
    0.17
    opr
    0.17
    Activations Density 0.590%

    No Known Activations