© 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. 14084
    Prev
    Next
    INDEX
    Explanations

    death and illness

    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
    åģļèµ·
    -0.21
    ç«ĭ
    -0.20
     default
    -0.19
    åģļä»Ģä¹Ī
    -0.18
    shape
    -0.18
    ä»İèĢĮ
    -0.18
    羣çļ®
    -0.18
    .figure
    -0.18
    ä¸Ģä¸ĭ
    -0.17
    è¿ĩæĿ¥
    -0.17
    POSITIVE LOGITS
    æĶ¯çº¿
    0.18
    æĸĹäºī
    0.18
    积èĵĦ
    0.18
    æĸ°åĨłçĹħæ¯Ĵ
    0.18
    追溯
    0.18
    æľŁéĸĵ
    0.18
    ä¸Ńåħ±
    0.18
    éĵį
    0.18
    å®ŀ践活åĬ¨
    0.18
    enerative
    0.17
    Activations Density 0.016%

    No Known Activations