© 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. 16745
    Prev
    Next
    INDEX
    Explanations

    MySQL database

    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
    .Xaml
    -0.23
    æ»ĩ
    -0.22
    æ»ĵ
    -0.21
    çī¯
    -0.21
    .xaml
    -0.21
    oit
    -0.20
    çij¶
    -0.20
    山路
    -0.19
    çŃĩ
    -0.19
     Romans
    -0.18
    POSITIVE LOGITS
    :mysql
    0.28
     pymysql
    0.26
     mysql
    0.26
    	mysql
    0.25
    (mysql
    0.25
    å¼Ģå°ģ
    0.24
     MySQL
    0.24
    MySQL
    0.24
     MySql
    0.24
    èııæ³½
    0.23
    Activations Density 0.109%

    No Known Activations