© 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. 13734
    Prev
    Next
    INDEX
    Explanations

    actions completed or undergoing

    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
    ä¸ĢåĪĩéĥ½
    -0.26
    çļĦä¸Ģéĥ¨åĪĨ
    -0.25
    åĴĮä»ĸçļĦ
    -0.23
    ä¸Ģåı¥
    -0.22
    ä¸Ģä¸Ŀ
    -0.21
    许å¤ļ
    -0.21
    ä¸Ģéĥ¨åĪĨ
    -0.21
    ä¸ĢåĪĩ
    -0.21
    ä»»ä½ķ人éĥ½
    -0.20
    ä¸įæĸŃå®ĮåĸĦ
    -0.20
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.27
    åIJĦèĩª
    0.26
    缸继
    0.24
    ä¸įåIJĮç¨ĭ度
    0.24
    éĻĨç»Ń
    0.23
    ãģĿãĤĮãģŀãĤĮ
    0.23
     themselves
    0.21
    该项
    0.20
    iage
    0.20
    INED
    0.19
    Activations Density 0.162%

    No Known Activations