© 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. 17317
    Prev
    Next
    INDEX
    Explanations

    click here or learn more

    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
    lein
    -0.21
    èģ¿
    -0.18
     Pac
    -0.18
    交代
    -0.18
     Lisp
    -0.18
    æµģåĬ¨
    -0.17
    èħŃ
    -0.17
    éģ½
    -0.17
     Lyn
    -0.17
     ÐĽÐ¸
    -0.17
    POSITIVE LOGITS
    女çİĭ
    0.20
     OPTIONAL
    0.20
    ç½Ķ
    0.19
    ingly
    0.18
    æIJ¬
    0.18
    ä¹ı
    0.17
    æĥ©æĪĴ
    0.17
    ynthesis
    0.17
    fact
    0.17
    æįı
    0.17
    Activations Density 0.320%

    No Known Activations