© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17121
    Prev
    Next
    INDEX
    Explanations

    Mac OS

    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
    Negative Logits
    <tag
    -0.20
     ká»·
    -0.20
    edReader
    -0.19
    iten
    -0.18
    ä¸ŃåĽ½ç§»åĬ¨
    -0.18
    ä¸ŃåĽ½çĶµä¿¡
    -0.18
    WithContext
    -0.17
    /cpp
    -0.17
    ertime
    -0.17
    æIJĢ
    -0.17
    POSITIVE LOGITS
    intosh
    0.24
    éĺµèIJ¥
    0.21
    çĭ¬æľīçļĦ
    0.20
    çļĦä¸ĢéĿ¢
    0.20
    ä»İæł¹æľ¬ä¸Ĭ
    0.20
    çĶŁæ¶¯
    0.20
    åĮĸè¿Ľç¨ĭ
    0.19
    ç»Ī端
    0.19
    çī¹æľīçļĦ
    0.19
    们çļĦ
    0.19
    Activations Density 0.023%

    No Known Activations