© 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. 10329
    Prev
    Next
    INDEX
    Explanations

    research projects topics

    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
    Negative Logits
     pornost
    -0.23
    å¾Īå¤ļæľĭåıĭ
    -0.22
    许å¤ļ人
    -0.22
    åħ¨çIJĥæľĢ大
    -0.22
    èĨĤ
    -0.22
     Ñģамого
    -0.21
    AutoSize
    -0.20
     Aviv
    -0.20
     Colomb
    -0.20
    LPARAM
    -0.19
    POSITIVE LOGITS
    çİ°çĬ¶
    0.26
    æ¡Īä¾ĭ
    0.25
    çłĶ究
    0.23
     project
    0.23
    åĪĨæŀIJ
    0.23
     researched
    0.22
    åģıåIJij
    0.22
     Kom
    0.22
    åīĸæŀIJ
    0.22
     topic
    0.21
    Activations Density 0.200%

    No Known Activations