© 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. 10900
    Prev
    Next
    INDEX
    Explanations

    company suffixes like LLC, Ltd

    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
    濯
    -0.21
    ениÑİ
    -0.19
    ë°¥
    -0.19
    åĪ«
    -0.19
    asion
    -0.19
    åĪĴ
    -0.18
    身åIJİ
    -0.18
    elon
    -0.18
    seen
    -0.18
    aler
    -0.18
    POSITIVE LOGITS
    æľīéĻIJåħ¬åı¸
    0.32
     LLC
    0.29
     Ltd
    0.27
    è¿Ļ家åħ¬åı¸
    0.26
     LTD
    0.25
    æľīéĻIJ责任
    0.25
    åħ¬åı¸åľ¨
    0.24
    å®ĺæĸ¹ç½ijç«Ļ
    0.23
    ç½ijç«Ļ
    0.22
    æľįåĬ¡å¹³åı°
    0.21
    Activations Density 0.231%

    No Known Activations