© 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. 11808
    Prev
    Next
    INDEX
    Explanations

    league play and opponents

    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
    èĩ´å¯Į
    -0.19
    äºĽä»Ģä¹Ī
    -0.19
    åįļçī©
    -0.18
    åİ»åģļ
    -0.18
    _gc
    -0.18
    _INF
    -0.18
     cul
    -0.18
     &_
    -0.18
    /reference
    -0.18
    æĿ¥è®¿
    -0.17
    POSITIVE LOGITS
    èĥľè´Ł
    0.20
    åIJ«
    0.20
    æĶ¾è¿ĩ
    0.19
    帮
    0.18
    åħ¬çĽĬæ´»åĬ¨
    0.18
    èģĶ
    0.18
    ä¹ĺ
    0.17
    è¿Ļ两
    0.17
    éłĵ
    0.17
    çľ¼è§Ĵ
    0.17
    Activations Density 0.008%

    No Known Activations