© 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. 15647
    Prev
    Next
    INDEX
    Explanations

    fire safety systems

    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
    åĨħ马
    -0.22
    综
    -0.21
    人群ä¸Ń
    -0.20
    ç½ijé¦ĸ页
    -0.20
    æ¼ī
    -0.20
    åŀ¢
    -0.20
    åľŃ
    -0.20
    ucer
    -0.19
    ector
    -0.19
    ONO
    -0.19
    POSITIVE LOGITS
    çŃīæĸ¹å¼ı
    0.27
    åı¯ä»¥å¸®åĬ©
    0.25
    æĪĸåħ¶ä»ĸ
    0.25
    æĪĸèĢħ
    0.24
    æĪĸ
    0.23
    .exist
    0.23
    æĪĸèĢħåħ¶ä»ĸ
    0.23
    æĿ¥
    0.22
    çļĦ帮åĬ©
    0.22
    帮åĬ©
    0.21
    Activations Density 0.179%

    No Known Activations