© 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. 10387
    Prev
    Next
    INDEX
    Explanations

    at home or work

    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
    æľªæĪIJ
    -0.22
    è¯Ŀ
    -0.21
    æ¯ĵ
    -0.21
    缸åIJĮçļĦ
    -0.21
    Enable
    -0.20
    å¥ģ
    -0.20
    ä¸ĢéĹ´
    -0.19
    çļĦç¡®
    -0.19
    virt
    -0.19
    æĪijèĩªå·±
    -0.19
    POSITIVE LOGITS
    reme
    0.23
    åĬŀåħ¬
    0.23
    å¤ĩ
    0.21
    adol
    0.20
    illions
    0.20
    åIJ¬åĪ°
    0.20
    å¾ĹçŁ¥
    0.20
    OTP
    0.19
    avia
    0.19
    ingleton
    0.18
    Activations Density 0.087%

    No Known Activations