© 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. 16759
    Prev
    Next
    INDEX
    Explanations

    love, loving, loved

    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
    \""
    -0.20
    èıŁ
    -0.20
    kers
    -0.19
    usra
    -0.19
    kich
    -0.19
    èħ¾é£ŀ
    -0.19
    æĶ¶åıĸ
    -0.18
    身份
    -0.18
    è°£è¨Ģ
    -0.18
    ä¸ĭæ»ij
    -0.17
    POSITIVE LOGITS
     âĿ¤
    0.23
    ä¹ĭæĥħ
    0.23
    å¾Īåĸľæ¬¢
    0.21
    âĻ¥
    0.21
    ä¸įåĸľæ¬¢
    0.20
    åĸľæ¬¢
    0.20
    åIJĥçļĦ
    0.20
    主æĦı
    0.20
    heart
    0.20
    åĸľçĪ±
    0.20
    Activations Density 0.097%

    No Known Activations