© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10327
    Prev
    Next
    INDEX
    Explanations

    sacred spaces and nature

    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
    Negative Logits
    èĩªè´Ł
    -0.25
    ä¸Ģçĵ¶
    -0.21
    eco
    -0.19
    EMON
    -0.19
    onium
    -0.19
    çľ¼éķľ
    -0.19
    éķ£
    -0.19
    è§īæĤŁ
    -0.18
    ä»ħ代表
    -0.18
    ä¸ĢåĿĹ
    -0.18
    POSITIVE LOGITS
    æ°´ä¸Ĭ
    0.21
     bÃło
    0.20
    éģĵçIJĨ
    0.20
    åľ¨çĶŁæ´»ä¸Ń
    0.20
     sola
    0.19
    èĪ¹ä¸Ĭ
    0.18
    å·©åĽº
    0.17
     lawy
    0.17
    æĪ·å¤ĸ
    0.17
    Moving
    0.17
    Activations Density 0.001%

    No Known Activations