© 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. 14399
    Prev
    Next
    INDEX
    Explanations

    matter or matters

    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
    趣åij³
    -0.20
    æĺİ亮
    -0.19
    aan
    -0.19
    oard
    -0.18
    icot
    -0.18
    äºĨä¸Ģ份
    -0.17
     обÑıзан
    -0.17
    éĢĤåIJĪèĩªå·±
    -0.17
    æij¸
    -0.17
     Babe
    -0.17
    POSITIVE LOGITS
    æŶåĢĻ
    0.21
    twig
    0.20
    å°±åľ¨äºİ
    0.19
    çĿĢæĢ¥
    0.19
    åľ¨ä¹İ
    0.19
    fully
    0.19
    çļĦæĺ¯
    0.19
    ingly
    0.19
    è¿Ļ个æŶåĢĻ
    0.19
    ç¨ĭ度
    0.19
    Activations Density 0.014%

    No Known Activations