© 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. 11466
    Prev
    Next
    INDEX
    Explanations

    face painting, makeup, tattoos, stamps

    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
    eric
    -0.23
    éĵ¾æĿ¡
    -0.21
    Ħ件
    -0.20
    æ³Į
    -0.20
    è¯Ńæ°Ķ
    -0.20
    lord
    -0.19
     Marl
    -0.19
     chain
    -0.19
    uilder
    -0.19
     Fav
    -0.18
    POSITIVE LOGITS
    æ¶Ĥ
    0.27
    人èĦ¸
    0.26
    èĦ¸
    0.26
    èĤ¤èī²
    0.26
    æ¶ĤæĬ¹
    0.24
    èĨı
    0.23
    临æŶ
    0.22
    ç²ĺ
    0.22
    é¢ľ
    0.21
    æļĤæŶ
    0.21
    Activations Density 0.026%

    No Known Activations