© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15169
    Prev
    Next
    INDEX
    Explanations

    Americas or American related entities

    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
    asti
    -0.18
    ori
    -0.18
    åľ¨åħ¨åĽ½
    -0.17
    积èĵĦ
    -0.17
    mist
    -0.17
    åij¨åĽ´
    -0.17
    -letter
    -0.17
     миÑĢа
    -0.17
     mistake
    -0.17
    ç²²
    -0.17
    POSITIVE LOGITS
    ลาย
    0.20
    countries
    0.20
    ä¹İ
    0.18
    ://%
    0.17
    frica
    0.17
    hooks
    0.17
    éĢļè¡Įè¯ģ
    0.16
     withholding
    0.16
    çī©ç§į
    0.16
     Ig
    0.16
    Activations Density 0.018%

    No Known Activations