© 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. 10388
    Prev
    Next
    INDEX
    Explanations

    in the

    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
     lifelong
    -0.19
    imed
    -0.19
    常年
    -0.19
    éĻ¢éĻ¢å£«
    -0.19
    çī¹å®ļ
    -0.19
     specific
    -0.18
    ç»ĪçĶŁ
    -0.18
    leton
    -0.18
    è¿Ļè¾ĪåŃIJ
    -0.18
     equally
    -0.18
    POSITIVE LOGITS
    /month
    0.21
    ä¼´éļıçĿĢ
    0.20
     taxp
    0.20
    åĴĮåľ°åĮº
    0.19
     اÙĦÙħاض
    0.19
     sourceMapping
    0.18
    缪
    0.18
    æĪIJ交éĩı
    0.18
    totals
    0.18
    æīĵæī®
    0.18
    Activations Density 0.034%

    No Known Activations