© 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. 17295
    Prev
    Next
    INDEX
    Explanations

    numbers one and two

    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
    èĢĹ
    -0.21
    éĵİ
    -0.20
    èĬĬ
    -0.19
    åIJ¯åıij
    -0.19
    å¾·æĭī
    -0.19
    ifu
    -0.18
    çİij
    -0.18
    è±¹
    -0.17
    deb
    -0.17
    侬
    -0.17
    POSITIVE LOGITS
    åĪĨåĪ«
    0.29
    åIJĦæľī
    0.27
    åĪĨåĪ«æĺ¯
    0.27
    åĪĨåĪ¥
    0.26
    两ç§į
    0.26
    åĪĨå¼Ģ
    0.23
    åĪĨåĪ«ä¸º
    0.23
    åIJĦèĩª
    0.23
     respectively
    0.22
    /or
    0.22
    Activations Density 0.239%

    No Known Activations