© 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. 16058
    Prev
    Next
    INDEX
    Explanations

    forming lists, checking details

    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
    æĺ¯ä¸Ģ座
    -0.26
    缮åīįæŃ£åľ¨
    -0.24
    æŁIJä¸Ģ
    -0.23
    åı¦å¤ĸä¸Ģ个
    -0.23
    æŁIJ个
    -0.23
    äºĨä¸Ģ声
    -0.22
    æŁIJç§į
    -0.22
    èļĮ
    -0.22
    è¯¥æł¡
    -0.22
    rets
    -0.21
    POSITIVE LOGITS
    åIJĦç§į
    0.42
    ä¸Ģ个个
    0.31
    åIJĦå¼ı
    0.29
    çĶļèĩ³
    0.29
     various
    0.28
    åIJĦ種
    0.28
    ç§įç§į
    0.27
    ä¸Ģ次次
    0.27
    æ¯ıä¸Ģ次
    0.26
    çŃīåIJĦç§į
    0.26
    Activations Density 0.158%

    No Known Activations