© 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. 10448
    Prev
    Next
    INDEX
    Explanations

    sponsor, sponsorship, partner, ambassador

    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
    å²ģ以ä¸ĭ
    -0.20
    ä¸Ĭ次
    -0.20
    便æ°ij
    -0.19
    pite
    -0.19
    orns
    -0.18
    ãģ¾ãģ¾
    -0.18
    oga
    -0.18
    æ§Ľ
    -0.18
    èºģ
    -0.17
    ngr
    -0.17
    POSITIVE LOGITS
     dudes
    0.23
    æĬī
    0.22
    åĴĮ个人
    0.19
    æĭĻ
    0.19
    éĿ¢æĿ¿
    0.19
    ä¸ŃåĽ½äºº
    0.18
    çºłçº·
    0.18
     ape
    0.17
    istical
    0.17
    åĨ²çªģ
    0.17
    Activations Density 0.005%

    No Known Activations