© 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. 10647
    Prev
    Next
    INDEX
    Explanations

    home and residential customers

    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
    èį¯æĿIJ
    -0.21
    ipi
    -0.21
    åı¯è§Ĥ
    -0.20
    åĮ»æĬ¤äººåijĺ
    -0.19
    åİĤæĪ¿
    -0.19
    åĬĿ
    -0.19
    çķ¿
    -0.18
    umi
    -0.18
    ç¬
    -0.18
    unding
    -0.18
    POSITIVE LOGITS
    个人
    0.27
    大ä¼Ĺ
    0.26
    家çĶ¨
    0.25
    æ°ijçĶ¨
    0.24
     personal
    0.24
     civilian
    0.24
    åħ¬ä¼Ĺ
    0.24
     household
    0.24
    ä¼ijéĹ²
    0.23
     retail
    0.21
    Activations Density 0.429%

    No Known Activations