© 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. 14725
    Prev
    Next
    INDEX
    Explanations

    drought, conflict, Koreans, Sahara

    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
    æ·®åįĹ
    -0.19
    è¡¢
    -0.19
    aval
    -0.19
     weekends
    -0.19
    åºĭ
    -0.19
    ä¸įåıĬ
    -0.18
    ads
    -0.18
    LOB
    -0.18
    éĻĦ
    -0.18
    Temp
    -0.18
    POSITIVE LOGITS
    obile
    0.21
     Mobile
    0.21
    alez
    0.20
    天æ°Ķ
    0.19
    æ³ķå®ļ
    0.19
    ä¸ĩçī©
    0.19
    -Mobile
    0.19
    -mobile
    0.18
    欧
    0.18
    chema
    0.18
    Activations Density 0.005%

    No Known Activations