© 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. 17118
    Prev
    Next
    INDEX
    Explanations

    excellence

    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
    ossal
    -0.24
    ä¸įä¸Ĭ
    -0.24
    Ñĩик
    -0.22
    幸ç¦ıæĦŁ
    -0.20
    sWith
    -0.20
    责任æĦŁ
    -0.20
    æ¶Īè´¹éľĢæ±Ĥ
    -0.17
    计ç®ĹåĻ¨
    -0.17
    ted
    -0.16
    ä¸įæ¸ħ
    -0.16
    POSITIVE LOGITS
    ä¹ĭè·¯
    0.21
    imb
    0.20
    ç²²
    0.19
     weir
    0.18
    elog
    0.18
    å¢ħ
    0.17
    ful
    0.17
    -minded
    0.16
    oring
    0.16
    on
    0.16
    Activations Density 0.005%

    No Known Activations