© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14595
    Prev
    Next
    INDEX
    Explanations

    whether you are

    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
    Not in Any Lists

    No Comments

    Negative Logits
     示
    -0.23
    å±IJ
    -0.22
     ÙĪعدÙħ
    -0.22
    éĻ¤éĿŀ
    -0.21
    æݧèĤ¡éĽĨåĽ¢
    -0.19
    :host
    -0.19
    â½°
    -0.19
    æľīçĶ¨çļĦ
    -0.19
    à¤Ĭ
    -0.18
    æĪijåİ»
    -0.18
    POSITIVE LOGITS
     already
    0.27
    å·²ç»ı
    0.26
     recently
    0.24
    æĥ³
    0.23
    already
    0.23
    å·²ç»ıåľ¨
    0.23
    åĪļåĪļ
    0.22
    å·²ç»ıæĪIJ为
    0.22
    å·²ç»ıæĺ¯
    0.21
    å´Ń
    0.21
    Activations Density 0.061%

    No Known Activations