© 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. 15056
    Prev
    Next
    INDEX
    Explanations

    colors and materials

    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
    å°ı游æĪı
    -0.23
    ç¬ijç¬ij
    -0.20
    éĶĩ
    -0.20
    -padding
    -0.19
    æĪ´ä¸Ĭ
    -0.19
    ä¸ĬçļĦ
    -0.19
    music
    -0.19
     ÑĥкÑĢа
    -0.18
    yen
    -0.18
     pie
    -0.18
    POSITIVE LOGITS
     cork
    0.22
    åľ¨çİ°åľº
    0.21
    æ°¸
    0.21
    å®ļåĪ¶
    0.21
    æĿľç»Ŀ
    0.20
    CurrentValue
    0.20
    åĸij
    0.19
    çħ
    0.19
    ä¸ĸ家
    0.19
    atoi
    0.19
    Activations Density 0.024%

    No Known Activations