© 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. 15266
    Prev
    Next
    INDEX
    Explanations

    Arab revolt

    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
    åīį沿
    -0.21
    ä¸įå½±åĵį
    -0.20
    ucer
    -0.19
     martin
    -0.19
    æIJº
    -0.19
    ä¿¡æģ¯æĬĢæľ¯
    -0.19
    Ìģ
    -0.18
     IGN
    -0.18
    çĪ±å¥½èĢħ
    -0.18
    Recovered
    -0.18
    POSITIVE LOGITS
    é¼»åŃIJ
    0.23
    BlockSize
    0.22
    anism
    0.19
    æĺ¯ä»Ģä¹Īåij¢
    0.19
    ç«ĸ
    0.19
    çļĦè¿ĩç¨ĭ
    0.19
    ORS
    0.18
    üler
    0.18
    åĪĽæĸ°é©±åĬ¨
    0.17
    ians
    0.17
    Activations Density 0.005%

    No Known Activations