© 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. 10892
    Prev
    Next
    INDEX
    Explanations

    professional associations or societies

    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
    åľ¨çĶŁæ´»ä¸Ń
    -0.24
    æ§ł
    -0.20
     MEDIATEK
    -0.20
     Câm
    -0.19
    avers
    -0.19
    mob
    -0.19
    çī¹éķ¿
    -0.18
    ç©¿è¿ĩ
    -0.18
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.18
     prime
    -0.18
    POSITIVE LOGITS
    æĪIJç«ĭäºİ
    0.26
    çŃīè¡Įä¸ļ
    0.21
    æĪIJåijĺ
    0.21
    æĪIJç«ĭ以æĿ¥
    0.20
    website
    0.19
    (groups
    0.19
    ,www
    0.19
    èµŀåĬ©
    0.19
    çľ¼çIJĥ
    0.18
    æĹĹä¸ĭçļĦ
    0.18
    Activations Density 0.073%

    No Known Activations