© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12416
    Prev
    Next
    INDEX
    Explanations

    email, Office, faculty, Studio, Services

    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
    大åŁİå¸Ĥ
    -0.26
    头æĿ¡
    -0.24
    å¤ļä¸ªåĽ½å®¶
    -0.24
    è¿Ļ家
    -0.23
     cities
    -0.23
    亿ä¸ĩ
    -0.22
    çĶ·äºº
    -0.22
    ä¸ªåĽ½å®¶
    -0.22
    è¿Ļ个è¡Įä¸ļ
    -0.22
    _WORLD
    -0.22
    POSITIVE LOGITS
    åIJĦéĥ¨éŨ
    0.33
    åħ¨æł¡
    0.33
    éĥ¨éŨ
    0.32
    æķĻèģĮå·¥
    0.29
     campus
    0.28
     department
    0.28
     faculty
    0.26
    çļĦåѦçĶŁ
    0.25
    对åѦçĶŁ
    0.25
    æł¡
    0.25
    Activations Density 0.134%

    No Known Activations