© 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. 14093
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by noun phrases

    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
    ä¸į说
    -0.21
    CAPE
    -0.18
    åĿı
    -0.18
    çĻ¾èĬ±
    -0.18
    ä¸Ģåij³
    -0.17
    yo
    -0.17
    æİIJ
    -0.17
    èıī
    -0.17
    istra
    -0.17
    AKER
    -0.17
    POSITIVE LOGITS
    è¿ĻäºĽéĥ½æĺ¯
    0.28
     respectively
    0.27
    åIJİèĢħ
    0.25
     alike
    0.24
    è¿Ļ两个
    0.24
    åĿĩåı¯
    0.23
    两èĢħ
    0.22
    éĥ½åı¯ä»¥
    0.22
    éĥ½ä¸į
    0.21
     latter
    0.21
    Activations Density 0.482%

    No Known Activations