© 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. 17171
    Prev
    Next
    INDEX
    Explanations

    game walkthroughs and FAQs

    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
    .fhir
    -0.23
    .vaadin
    -0.23
    	iNdEx
    -0.22
    fit
    -0.22
    ariat
    -0.21
    _kwargs
    -0.21
     fit
    -0.21
    isper
    -0.21
    angelo
    -0.20
    anel
    -0.20
    POSITIVE LOGITS
    游æĪıä¸Ń
    0.31
    åľ¨æ¸¸æĪıä¸Ń
    0.30
    ä½ľå¼Ĭ
    0.29
    该游æĪı
    0.29
    çİ©æ³ķ
    0.28
    æĬĢå·§
    0.28
    æĪIJåĬŁçİĩ
    0.28
    æĶ»çķ¥
    0.28
    çļĦ帮åĬ©
    0.27
    iếc
    0.27
    Activations Density 0.062%

    No Known Activations