© 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. 15602
    Prev
    Next
    INDEX
    Explanations

    greetings and introductions

    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
    ografia
    -0.21
    鸡汤
    -0.21
    éĢłç¦ı
    -0.20
    ingen
    -0.20
    裤åŃIJ
    -0.19
    èIJ¥åħ»
    -0.19
    é«ĺä»·
    -0.19
    ä¸įåłª
    -0.19
    bane
    -0.19
    è·£
    -0.19
    POSITIVE LOGITS
    éĹ®åĢĻ
    0.38
     greeting
    0.31
     greet
    0.29
     greeted
    0.22
     greetings
    0.22
    åijĬåĪ«
    0.22
    ðŁijĭ
    0.20
    æīĵæĭĽåij¼
    0.20
     goodbye
    0.20
     welcome
    0.20
    Activations Density 0.027%

    No Known Activations