© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12493
    Prev
    Next
    INDEX
    Explanations

    legal professions and firms

    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
    commission
    -0.23
    äºı
    -0.23
    å¿ĥçIJĨåѦ
    -0.21
    å¿ĹæĦ¿
    -0.21
    äººæł¼
    -0.20
    ç«Ļéķ¿
    -0.20
    Commission
    -0.19
    ç§ijæķĻ
    -0.18
    æĬ¹
    -0.18
    æķĻèĤ²åŁ¹è®Ń
    -0.18
    POSITIVE LOGITS
    帮åĬ©ä¼ģä¸ļ
    0.23
    èµĦæľ¬å¸Ĥåľº
    0.23
    éĢĤæŶ
    0.22
    èªī
    0.22
    çĶ¦
    0.21
    对åħ¬åı¸
    0.21
    çļĦéĩį大
    0.20
     Byrne
    0.19
    ä¸Ģ个å¤ļ
    0.19
    èѬ
    0.19
    Activations Density 0.045%

    No Known Activations