© 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. 17307
    Prev
    Next
    INDEX
    Explanations

    bizarre, surreal, wacky, ridiculous

    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
    usher
    -0.21
     велик
    -0.20
     Trap
    -0.19
    è°®
    -0.18
    åIJİå¤ĩ
    -0.18
    æģļ
    -0.17
    é£İåħī
    -0.17
    ainless
    -0.17
     ascend
    -0.17
    éĻ·
    -0.17
    POSITIVE LOGITS
    åı¤æĢª
    0.27
    æľī趣çļĦ
    0.24
     conco
    0.23
    éĻĭ
    0.22
    å¥ĩèij©
    0.22
    éªĩ
    0.22
    çİ©æĦı
    0.22
    ä¹İ
    0.21
    å¥ĩå¼Ĥ
    0.21
    ditor
    0.21
    Activations Density 0.047%

    No Known Activations