© 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. 17213
    Prev
    Next
    INDEX
    Explanations

    duration and length

    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
    jc
    -0.20
    年代
    -0.20
    emma
    -0.18
    å¿Ļ
    -0.18
    jk
    -0.18
    æıŃ示
    -0.18
    èĬ¦
    -0.18
    强
    -0.18
     hem
    -0.17
    eted
    -0.17
    POSITIVE LOGITS
    æľĢéķ¿
    0.24
    éķ¿çŁŃ
    0.24
    ä¸įåĬ¨
    0.21
     lengths
    0.21
    æĭ©
    0.20
     Ø·ÙĪÙĬÙĦØ©
    0.19
    å¾Īéķ¿
    0.19
    ãĥ¯ãĥ³
    0.19
    éķ¿åº¦
    0.19
    æĹħç¨ĭ
    0.19
    Activations Density 0.007%

    No Known Activations