© 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. 16798
    Prev
    Next
    INDEX
    Explanations

    if then

    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
    æĺ¯æĪijåĽ½
    -0.23
    å°±æĺ¯åľ¨
    -0.20
    à¸Ľà¸£à¸°à¸ªà¸ļ
    -0.20
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.20
    è·Ľ
    -0.20
    å°±æĺ¯ä¸ºäºĨ
    -0.20
     illegally
    -0.20
    .getDescription
    -0.19
    çĺħ
    -0.19
    å°±æĺ¯è¿Ļæł·
    -0.19
    POSITIVE LOGITS
    åºĶåıĬæŶ
    0.26
    缸åºĶçļĦ
    0.25
    åĪĻ
    0.24
    ç«ĭåį³
    0.23
    åıĬæŶ
    0.23
    åı¯éĢļè¿ĩ
    0.23
    ä¸Ģå¾ĭ
    0.23
    è¦ģåıĬæŶ
    0.22
    ä¼ij
    0.22
    缸åºĶ
    0.21
    Activations Density 0.135%

    No Known Activations