© 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. 14375
    Prev
    Next
    INDEX
    Explanations

    football federations and cups

    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
    çıŃ主任
    -0.21
    åĩºåĽ½çķĻåѦ
    -0.21
    éĶĹ
    -0.20
    éģĦ
    -0.20
    indle
    -0.20
    /umd
    -0.19
    nonnull
    -0.18
    handlers
    -0.18
    è¿ĻåĦ¿
    -0.17
    é¦ı
    -0.17
    POSITIVE LOGITS
    éĢļ
    0.19
    _tran
    0.19
    åľºæĻ¯
    0.19
    itta
    0.18
     pac
    0.18
     Pac
    0.18
     penalty
    0.18
    龸çİĭ
    0.18
     Africa
    0.17
    éĢļè¡Įè¯ģ
    0.17
    Activations Density 0.014%

    No Known Activations