© 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. 14470
    Prev
    Next
    INDEX
    Explanations

    listing conjunctions and punctuation

    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
    nable
    -0.23
    åĽŀæĥ³
    -0.20
    sume
    -0.20
    æIJŀå®ļ
    -0.19
    æĪijä¸įçŁ¥éģĵ
    -0.19
    ko
    -0.19
    covers
    -0.18
    æľĢåıĹ
    -0.18
    åĨĬ
    -0.18
    éģĩåĪ°
    -0.18
    POSITIVE LOGITS
    äºİæĺ¯
    0.25
    ä¹ŁçŁ¥éģĵ
    0.24
    ä»İèĢĮ
    0.23
    è¿ĽèĢĮ
    0.23
    ucer
    0.22
    åħ¥å¸Ĥ
    0.22
    æīĢä»¥åľ¨
    0.21
    为ä¹ĭ
    0.20
    éģĤ
    0.20
    azu
    0.20
    Activations Density 0.118%

    No Known Activations