© 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. 13313
    Prev
    Next
    INDEX
    Explanations

    gaming context, sports, or competition

    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
     reportedly
    -0.22
    å¾ĹåĪ°äºĨ
    -0.22
    éĢı
    -0.21
     punch
    -0.20
    çij°
    -0.19
    å¼Ģåıij
    -0.19
    è¡Įä¸ļ
    -0.19
    çŃij
    -0.19
     industry
    -0.19
    éĽªèĬ±
    -0.19
    POSITIVE LOGITS
    ä»»ä½ķæŶåĢĻ
    0.30
    çĬ¯è§Ħ
    0.28
    æ¯ĶèµĽä¸Ń
    0.26
    åįķèģĮä¸ļ
    0.25
    çī¹æ®ĬæĥħåĨµ
    0.25
    ä»»ä½ķ人
    0.24
    ä»»ä½ķä¸Ģ个
    0.24
    åľ¨çݩ家ä¸Ń
    0.24
     обÑıзан
    0.24
    ä»»ä½ķå½¢å¼ı
    0.24
    Activations Density 0.041%

    No Known Activations