© 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. 14616
    Prev
    Next
    INDEX
    Explanations

    education reform

    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
    åįķ身
    -0.23
    æĮĸæİĺ
    -0.21
    人åĵ¡
    -0.21
    综åIJĪä½ĵ
    -0.20
    ç»ıèIJ¥æ´»åĬ¨
    -0.20
    人åijĺ
    -0.20
    æķijæĬ¤
    -0.20
    åĨľåī¯
    -0.19
    临æŶ
    -0.19
    åİĤåĮº
    -0.19
    POSITIVE LOGITS
    æĶ¹éĿ©
    0.29
    éĹ®è´£
    0.28
    åħ¨åĽ½
    0.24
    æĭ¨
    0.24
     reforms
    0.24
     reform
    0.24
     sprint
    0.22
    çĽ¯çĿĢ
    0.21
    è´¨éĩı
    0.21
    æ¿ĢåĬ±
    0.20
    Activations Density 0.016%

    No Known Activations