© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17081
    Prev
    Next
    INDEX
    Explanations

    interesting and funny things

    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
    Negative Logits
    主è¦ģåĨħ容
    -0.23
    éĩįè¦ģåĨħ容
    -0.22
    æīĢéľĢè¦ģçļĦ
    -0.22
     arsch
    -0.21
    amt
    -0.20
    inding
    -0.19
    ç¡®è¯Ĭ
    -0.19
    ⼰
    -0.19
     essentials
    -0.18
    -scrollbar
    -0.18
    POSITIVE LOGITS
    æľī趣
    0.31
     interesting
    0.27
    æľīæĦıæĢĿ
    0.27
     Interesting
    0.26
     interess
    0.25
    Interesting
    0.24
    æľī趣çļĦ
    0.24
    æľīæĦıæĢĿçļĦ
    0.23
    ä¹Łå¾Ī
    0.23
    interesting
    0.22
    Activations Density 0.077%

    No Known Activations