© 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. 13355
    Prev
    Next
    INDEX
    Explanations

    AC electrical power and conversions

    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
    头éĥ¨
    -0.19
     sandwich
    -0.18
    ctr
    -0.18
    ema
    -0.17
    è¯ļæĦı
    -0.17
     Nimbus
    -0.17
     Highlight
    -0.17
    åѤç«ĭ
    -0.17
    æ¼Ĥæµģ
    -0.17
    âľį
    -0.16
    POSITIVE LOGITS
    å¤ĸçķĮ
    0.24
    çĽij管éĥ¨éŨ
    0.22
    åĨ¶
    0.22
    çĶµç½ij
    0.21
     Ùħباشرة
    0.20
    æłī
    0.20
    SYS
    0.19
    åĺĪ
    0.19
    æłĩåĩĨ
    0.19
    éĩįè¦ģæĮĩ示
    0.19
    Activations Density 0.054%

    No Known Activations