© 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. 13060
    Prev
    Next
    INDEX
    Explanations

    substantial exit barrier

    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
    çļĦçħ§çīĩ
    -0.23
    åIJ¬è¯¾
    -0.22
    درج
    -0.22
    åħ®
    -0.22
    æ¯ıå¹´éĥ½
    -0.21
    è®°å½ķ
    -0.20
    讲课
    -0.20
    çļĦåIJĦç§į
    -0.19
    æĪijè®°å¾Ĺ
    -0.19
    æĻļä¸Ĭ
    -0.19
    POSITIVE LOGITS
    åŃº
    0.28
    æĺ¯å¤ļä¹Ī
    0.27
     indeed
    0.24
    ä¸įåıªæĺ¯
    0.24
    å¤ļä¹Ī
    0.23
    åŃĺåľ¨ä¸Ģå®ļ
    0.23
    ä¸įä»ħä»ħæĺ¯
    0.22
    çļĦç¡®æĺ¯
    0.21
    ç¡®å®ŀ
    0.21
    çĿĢå®ŀ
    0.21
    Activations Density 0.167%

    No Known Activations