© 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. 11219
    Prev
    Next
    INDEX
    Explanations

    top twenty chart

    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
    æĴŃ
    -0.19
    åħļç»Ħ
    -0.18
    åªļ
    -0.18
    ä¸ĸçķĮä¸Ģæµģ
    -0.18
    lings
    -0.18
    æĪ¾
    -0.18
    zel
    -0.18
    _SOCKET
    -0.18
    æ·
    -0.17
     Gates
    -0.17
    POSITIVE LOGITS
    ä¹ĭåĬ¿
    0.20
    åĮ»åѦéĻ¢
    0.20
    俱
    0.19
    LLU
    0.19
    ç»ıæµİæĬĢæľ¯
    0.19
     Laundry
    0.18
    erten
    0.18
    oran
    0.18
    çıįçıł
    0.18
     loose
    0.18
    Activations Density 0.001%

    No Known Activations