© 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. 16699
    Prev
    Next
    INDEX
    Explanations

    boxing, boxers, fights

    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
    æ²Ĩ
    -0.20
     Cavaliers
    -0.20
    æķ£æŃ¥
    -0.19
    esium
    -0.19
    лей
    -0.19
    elves
    -0.19
    éģĽ
    -0.18
    æĬĹè®®
    -0.18
    Disney
    -0.18
     unanim
    -0.18
    POSITIVE LOGITS
    æĭ³
    0.30
    boxing
    0.28
     boxing
    0.26
     Boxing
    0.24
     punching
    0.22
    ä¸ĸçķĮ级
    0.20
    èģĮä¸ļçĶŁæ¶¯
    0.20
     boxer
    0.20
     professionnel
    0.20
    æīĵèµ¢
    0.19
    Activations Density 0.052%

    No Known Activations