© 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. 17042
    Prev
    Next
    INDEX
    Explanations

    photographing or shooting

    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
    修为
    -0.21
    太快
    -0.19
    åĵį
    -0.19
    佬
    -0.18
    ä¸įå®ī
    -0.18
    读åIJİ
    -0.18
    åľ¨åħ¶
    -0.18
    åĸĬ
    -0.18
    å¼łè´´
    -0.17
    èijŃ
    -0.17
    POSITIVE LOGITS
    åij¨æľŁ
    0.21
    imony
    0.20
    zs
    0.20
     hierarchy
    0.20
     lic
    0.19
     LIC
    0.19
    å°¸
    0.18
    æķ´ä¸ªäºº
    0.18
    äºĨå¾Īå¤ļ
    0.18
    è¿Ļæł·ä¸ĢæĿ¥
    0.18
    Activations Density 0.012%

    No Known Activations