© 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. 14221
    Prev
    Next
    INDEX
    Explanations

    centuries or years referring to time periods

    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
    缮åīįæŃ£åľ¨
    -0.28
     currently
    -0.27
    缮åīį
    -0.25
    çİ°éĺ¶æ®µ
    -0.23
    çİ°ä»»
    -0.23
    åĽŀæĿ¥äºĨ
    -0.23
    å½ĵä¸ĭ
    -0.22
    çľ¼ä¸ĭ
    -0.22
    currently
    -0.22
    Currently
    -0.22
    POSITIVE LOGITS
    åIJİæľŁ
    0.29
    ä¸Ģ缴åĪ°
    0.29
     later
    0.29
    缴èĩ³
    0.28
    åIJİæĿ¥
    0.28
    缴åĪ°
    0.28
    æĹ¶æľŁçļĦ
    0.27
    later
    0.26
    è¿Ħ
    0.26
    æĹ¶æľŁ
    0.24
    Activations Density 0.267%

    No Known Activations