© 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. 16669
    Prev
    Next
    INDEX
    Explanations

    cooperative effort and shared resources

    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
    çĶŁæ¶¯
    -0.22
    ç²īä¸Ŀ
    -0.21
    é«ĺ端
    -0.21
    éĢĨè¢Ń
    -0.20
    å¤ĸèµĦ
    -0.20
    åıĺçİ°
    -0.20
    ç²ī
    -0.20
    ä¸İä¸ŃåĽ½
    -0.20
    vine
    -0.19
    åħħæĸ¥
    -0.19
    POSITIVE LOGITS
    å½¼æѤ
    0.66
    åIJĦèĩª
    0.58
    äºĴ缸
    0.57
    缸äºĴ
    0.54
     mutual
    0.51
    åIJĦèĩªçļĦ
    0.50
    åħ±åIJĮ
    0.50
    ãģĬäºĴãģĦ
    0.48
     shared
    0.44
     mutually
    0.44
    Activations Density 0.130%

    No Known Activations