© 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. 11712
    Prev
    Next
    INDEX
    Explanations

    thank you much

    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
     Spacer
    -0.21
    ä¸Ģçľ¼
    -0.20
    è²Įä¼¼
    -0.20
    ä¸ºçĽ®æłĩ
    -0.19
    ä¸Ģ天
    -0.19
    足迹
    -0.19
    imb
    -0.18
    Spoiler
    -0.18
    ä¸Ģæĸ¹
    -0.18
    è¿«
    -0.18
    POSITIVE LOGITS
    ãģ¨ãĤĤ
    0.20
    ãģĬé¡ĺãģĦ
    0.20
    æİĺ
    0.20
    贯彻
    0.20
    æķ¬ä¸ļ
    0.19
    theless
    0.18
    æĶ®
    0.17
    æĬĬè¿Ļ个
    0.17
    两级
    0.17
    çļĦå¿ĥæĥħ
    0.17
    Activations Density 0.030%

    No Known Activations