© 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. 13098
    Prev
    Next
    INDEX
    Explanations

    developed new technology

    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
    plx
    -0.25
    ä¸ŃåĽ½ç½ij游
    -0.23
    é£ij
    -0.23
    inoa
    -0.21
    æĹ¶æ®µ
    -0.21
    游æĪı代
    -0.21
    essional
    -0.20
     заÑĢегиÑģÑĤ
    -0.20
    Nintendo
    -0.20
    åľ¨çݩ家ä¸Ń
    -0.20
    POSITIVE LOGITS
    çłĶåıij
    0.42
    å¼Ģåıij
    0.41
    çłĶåĪ¶
    0.40
    çļĦçłĶåıij
    0.35
     technology
    0.34
     patented
    0.32
    æĬĢæľ¯
    0.32
    åİŁåŀĭ
    0.32
    çłĶ究
    0.32
    æĶ¹è¿Ľ
    0.32
    Activations Density 0.267%

    No Known Activations