© 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. 13844
    Prev
    Next
    INDEX
    Explanations

    quality of life

    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
    elo
    -0.23
    é»ĺ
    -0.20
     repl
    -0.19
    Coffee
    -0.19
    ä»ģ
    -0.18
     trie
    -0.18
    åijĬ
    -0.18
    两ä¸ī
    -0.18
    梯éĺŁ
    -0.17
    GetProperty
    -0.17
    POSITIVE LOGITS
    çĶŁæ´»è´¨éĩı
    0.35
     жизни
    0.24
     life
    0.21
    Endpoints
    0.21
     LIFE
    0.20
    çĶŁæ´»æ°´å¹³
    0.20
    æĮĪ
    0.19
    REAM
    0.19
    ä½ĵéªĮ
    0.19
    ä¸į满æĦı
    0.19
    Activations Density 0.054%

    No Known Activations