© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10641
    Prev
    Next
    INDEX
    Explanations

    by the

    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
    æĪIJ为ä¸ĢåIJį
    -0.19
    çŀ³
    -0.19
    èĤ²äºº
    -0.19
    èĢĨ
    -0.18
    ewriter
    -0.18
    detail
    -0.18
    形容
    -0.18
    индивид
    -0.17
    uddle
    -0.17
    åĹĵ
    -0.17
    POSITIVE LOGITS
     lack
    0.24
    ç»ıèIJ¥æ´»åĬ¨
    0.22
    ä»Ģä¹ĪåİŁåĽł
    0.21
     exposure
    0.21
    è¿Ļåľº
    0.20
    äºĨä¸Ģåľº
    0.20
    æĹ¶ä»£çļĦ
    0.20
     pressure
    0.19
     prolonged
    0.19
    -ca
    0.19
    Activations Density 0.195%

    No Known Activations