© 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. 17064
    Prev
    Next
    INDEX
    Explanations

    premolars and incisors

    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
    èıľé¸Ł
    -0.22
    æ·ĺ
    -0.21
    æ·ħ
    -0.19
    hole
    -0.19
    uala
    -0.19
    lyn
    -0.18
    ä¸ľè¥¿
    -0.18
     Provid
    -0.18
    ilder
    -0.18
     MOR
    -0.18
    POSITIVE LOGITS
    -Cs
    0.19
    å¤ļãģĦ
    0.18
     Wein
    0.17
    å·¥åľ°
    0.17
    轨
    0.17
    å¾µ
    0.17
    æĦĪ
    0.17
    çĮ¢
    0.17
     Pett
    0.17
    æľĢéļ¾
    0.16
    Activations Density 0.830%

    No Known Activations