© 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. 10381
    Prev
    Next
    INDEX
    Explanations

    fix-ups or build

    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
    еÑĢÑĮ
    -0.21
     smugg
    -0.20
    ç³»
    -0.20
    麾
    -0.19
    kest
    -0.19
    æĶ¾å¼Ģ
    -0.19
    rance
    -0.18
    éģº
    -0.18
    åĸ·
    -0.18
    çķħéĶĢ
    -0.18
    POSITIVE LOGITS
    åĿª
    0.24
    squ
    0.22
     dá»±ng
    0.22
    åĬ¨å·¥
    0.21
     duplex
    0.21
    åµ´
    0.21
     HUD
    0.20
    æŀķ头
    0.20
    æ¡´
    0.20
     безоп
    0.19
    Activations Density 0.004%

    No Known Activations