© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12560
    Prev
    Next
    INDEX
    Explanations

    social interactions and dating

    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
    为广大
    -0.22
    åħ¨ç¤¾ä¼ļ
    -0.21
    åºŀ大
    -0.20
    çĪº
    -0.19
    解åĨ³
    -0.19
    严åİīæīĵåĩ»
    -0.19
    åıijå¸ĥåħ¬åijĬ
    -0.19
     Throne
    -0.19
    çĽij
    -0.19
    ovsky
    -0.19
    POSITIVE LOGITS
    对æĸ¹
    0.27
    约ä¼ļ
    0.25
    社交
    0.25
    è¯ķæİ¢
    0.24
    è§ģéĿ¢
    0.23
    æľīæĦıæĢĿ
    0.23
     mutual
    0.22
    交å¾Ģ
    0.22
    å½ĵ天
    0.22
    ä¸įè¿ĩ
    0.22
    Activations Density 0.052%

    No Known Activations