© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13861
    Prev
    Next
    INDEX
    Explanations

    rebuilding and reconstruction

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĭ¿æĿ¥
    -0.19
    é«ĺæīĭ
    -0.17
    ToArray
    -0.17
     verge
    -0.17
    æĢ¥å¿Ļ
    -0.17
    ä¸Ĭåİ»
    -0.16
    repeat
    -0.16
    åī¯ç§ĺ书éķ¿
    -0.16
    beer
    -0.16
     lore
    -0.16
    POSITIVE LOGITS
    éĩį建
    0.19
    æĮ¯åħ´
    0.18
     Emin
    0.18
    inking
    0.18
     MyApp
    0.17
    zyst
    0.17
    structions
    0.17
    anz
    0.17
    bose
    0.17
    azar
    0.17
    Activations Density 0.007%

    No Known Activations