© 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. 15432
    Prev
    Next
    INDEX
    Explanations

    time periods

    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
    éĤ£ä¹Īå¤ļ
    -0.22
    æ¯ı次éĥ½
    -0.21
    屯
    -0.21
    çĶ¨äºĨ
    -0.21
     Haus
    -0.20
    åįķä¸Ģ
    -0.20
    asin
    -0.19
     gam
    -0.19
    cx
    -0.19
    èĮ¨
    -0.19
    POSITIVE LOGITS
     اÙĦÙħÙĤبÙĦ
    0.26
    åıijå±ķ缮æłĩ
    0.23
    ä¸ĭä¸ĢæŃ¥
    0.23
    æİ¥ä¸ĭæĿ¥
    0.22
     próxima
    0.22
    ä¸ĭä¸Ģ个
    0.21
    è¡Įäºĭ
    0.21
    èĢĨ
    0.21
    next
    0.20
     nächsten
    0.20
    Activations Density 0.040%

    No Known Activations