© 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. 12881
    Prev
    Next
    INDEX
    Explanations

    larger than, founded, scoring, winning

    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
    ÑĦи
    -0.23
    è¿Ļæĺ¯ä¸Ģç§į
    -0.23
     amp
    -0.19
    æĻı
    -0.19
    è¿Ļæĺ¯
    -0.18
    è¿Ļæĺ¯æĪij们
    -0.18
    åıĹ害
    -0.18
    æħķ
    -0.18
    è¿Ļ个è¡Įä¸ļ
    -0.17
    ç°ĩ
    -0.17
    POSITIVE LOGITS
    ä¸įä½Ĩ
    0.26
    çĶļèĩ³
    0.21
    éĵ¨
    0.21
    好似
    0.20
    åıįèĢĮ
    0.20
    好åĩłä¸ª
    0.19
    纬
    0.19
    ä¸įä»ħ
    0.19
    常说
    0.19
    SYSTEM
    0.18
    Activations Density 0.338%

    No Known Activations