© 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. 10581
    Prev
    Next
    INDEX
    Explanations

    or other

    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
     cá»Ń
    -0.24
    åįī
    -0.22
    afia
    -0.20
    æĶ¾å¿ĥ
    -0.20
    .lu
    -0.20
    æ¼ł
    -0.19
    	fflush
    -0.19
    vu
    -0.19
    åĭĸ
    -0.19
    ascus
    -0.18
    POSITIVE LOGITS
    类似çļĦ
    0.35
     similarly
    0.30
     similar
    0.29
    类似
    0.28
    ä¸İæѤ
    0.27
    ãĤĤãģ£ãģ¨
    0.27
    åħ¶å®ĥ
    0.25
    çĽ¸ä¼¼
    0.23
     other
    0.23
    åĪ«çļĦ
    0.23
    Activations Density 0.108%

    No Known Activations