© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15325
    Prev
    Next
    INDEX
    Explanations

    G20 countries

    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
    _multiplier
    -0.20
     Shr
    -0.19
    uger
    -0.19
    éŨæĪ·
    -0.19
    èĬ
    -0.18
    æĹłäºº
    -0.18
    绿åĮĸ
    -0.18
    红æĹĹ
    -0.17
    æ¯ıä½į
    -0.17
    ä»ĸåıĪ
    -0.17
    POSITIVE LOGITS
    èIJĮ
    0.19
    大ä¼Ĺ
    0.18
    éĥ¨åĪĨåľ°åĮº
    0.18
     Storm
    0.18
    kers
    0.18
     cục
    0.18
    é«ĺå±Ĥ次
    0.18
     Womens
    0.18
     HQ
    0.18
    è¯ģåĪ¸
    0.17
    Activations Density 0.002%

    No Known Activations