© 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. 16859
    Prev
    Next
    INDEX
    Explanations

    embarrassment and shame

    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
    æĿ³
    -0.22
    æĦıå¢ĥ
    -0.20
    æĸ¹éĴĪ
    -0.20
    åŀĦ
    -0.18
    ä¿Ŀåħ»
    -0.18
    yer
    -0.18
    struct
    -0.17
    æ¹ĵ
    -0.17
    nie
    -0.17
    西éĥ¨
    -0.17
    POSITIVE LOGITS
    ç¾ŀ
    0.21
    ingly
    0.20
    /assert
    0.19
     Ñģобой
    0.18
    裤
    0.18
    浪费
    0.17
    èĢ»
    0.17
    æĢį
    0.17
     latter
    0.16
     admission
    0.16
    Activations Density 0.010%

    No Known Activations