© 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. 10843
    Prev
    Next
    INDEX
    Explanations

    money, businesses, prosecution, role

    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
    éļħ
    -0.20
     Sno
    -0.20
     Cran
    -0.19
    åĵī
    -0.19
    å¼Ĥ
    -0.19
    ãĤ·ãĤ§
    -0.19
    æ·±åħ¥äººå¿ĥ
    -0.19
    æĶ»çķ¥
    -0.18
    å¾Ĺ天çĭ¬åİļ
    -0.18
    .df
    -0.18
    POSITIVE LOGITS
    æĪĸæĺ¯
    0.27
    æĪĸèĢħåħ¶ä»ĸ
    0.27
    æĪĸèĢħæĺ¯
    0.27
    æĪĸåħ¶ä»ĸ
    0.27
     either
    0.26
     or
    0.26
    æĪĸèĢħ
    0.26
     hoặc
    0.26
     atau
    0.25
    íķĺê±°ëĤĺ
    0.25
    Activations Density 0.102%

    No Known Activations