© 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. 10421
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è¿Ľä¸ĢæŃ¥
    -0.20
    æĥº
    -0.19
     fier
    -0.19
     allegedly
    -0.19
    THR
    -0.19
     Detaylı
    -0.19
    ä»ĸ们çļĦ
    -0.18
    åı¦å¤ĸ
    -0.18
    缸åħ³
    -0.18
     further
    -0.18
    POSITIVE LOGITS
    çĥ
    0.21
    argout
    0.19
    setType
    0.19
    ä¸įä½ı
    0.19
    /***/
    0.19
    vasion
    0.19
    eros
    0.18
    .gnu
    0.18
    ï¼Īç¬ij
    0.18
    ä¸įé«ĺ
    0.18
    Activations Density 0.148%

    No Known Activations