© 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. 16943
    Prev
    Next
    INDEX
    Explanations

    games and matches

    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
    çĿ¡åīį
    -0.22
    åĩłå®¶
    -0.21
    好åIJĹ
    -0.21
    å¸ĪèµĦ
    -0.20
    iggers
    -0.20
    åĩłä½į
    -0.19
     gia
    -0.19
    ä¸įçĶĺ
    -0.19
    æĪijçİ°åľ¨
    -0.19
    æĭĻ
    -0.19
    POSITIVE LOGITS
    夹
    0.20
    OperationException
    0.20
     Stat
    0.19
    åĬ³ç´¯
    0.19
    æŀ«
    0.18
    ç»ıæµİ
    0.18
    ãģ©ãģĵãĤį
    0.18
     televised
    0.18
    ä¸Ģä½ĵåĮĸ
    0.18
    åħ¼
    0.17
    Activations Density 0.021%

    No Known Activations