© 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. 17228
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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
    éļĶçĿĢ
    -0.22
    æ¯ıéļĶ
    -0.21
    æ¯ı次
    -0.20
    éĤ
    -0.20
    æ¯
    -0.20
    ä¸ĭ次
    -0.19
    çݰ代çī©æµģ
    -0.19
     overd
    -0.19
    à¹ģà¸Ļ
    -0.19
    PURE
    -0.19
    POSITIVE LOGITS
    omb
    0.21
     половин
    0.20
    ensed
    0.20
    umph
    0.20
    late
    0.19
    è¡¥åħħ
    0.19
    å¼Ģå§ĭ
    0.19
    æŶå°ļ
    0.19
    ideo
    0.18
    неÑĢ
    0.18
    Activations Density 0.070%

    No Known Activations