© 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. 17088
    Prev
    Next
    INDEX
    Explanations

    nonprecedential publication restriction

    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
    éĴµ
    -0.20
    -0.19
     stead
    -0.19
     bare
    -0.18
    abus
    -0.18
    æĭĸ
    -0.18
     Bes
    -0.18
    á
    -0.17
    éĶ¦
    -0.17
    æĵį纵
    -0.17
    POSITIVE LOGITS
    æĶ¾å¼Ģ
    0.23
    æŃ£å¸¸ä½¿çĶ¨
    0.23
    çĻ¾å¹´
    0.21
    éĻ¤éĿŀ
    0.21
    ä»ħä¾Ľ
    0.21
    å¼ĢæĶ¾
    0.20
    对å¤ĸå¼ĢæĶ¾
    0.19
    æĿĥçĽĬ
    0.19
    apers
    0.18
     Troll
    0.18
    Activations Density 0.029%

    No Known Activations