© 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. 15201
    Prev
    Next
    INDEX
    Explanations

    "what" following question marks

    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
     Fif
    -0.22
    åı¸
    -0.20
    æĢ»èĢĮè¨Ģ
    -0.19
    éģĩä¸Ĭ
    -0.18
    _safe
    -0.18
    _LS
    -0.18
    ç®Ĺæĺ¯
    -0.18
     addslashes
    -0.18
     tac
    -0.18
     Moody
    -0.18
    POSITIVE LOGITS
    æĢİä¹ĪåĽŀäºĭ
    0.27
    ç«Ł
    0.23
    ç«Łæĺ¯
    0.22
    æķ¢
    0.20
    以为
    0.20
    æĢİä¹Īåı¯èĥ½
    0.20
    ä»Ģä¹ĪæĦıæĢĿ
    0.20
    ãģ¾ãģķ
    0.19
    åIJ¬è¯´è¿ĩ
    0.19
    ç«ŁçĦ¶
    0.19
    Activations Density 0.045%

    No Known Activations