© 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. 10369
    Prev
    Next
    INDEX
    Explanations

    occur, should, chance, decide

    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
    大家åĪĨ享
    -0.21
    好å¤ļ
    -0.21
    çľĭäºĨä¸Ģ
    -0.20
    å¦Ĥæŀľæ²¡æľī
    -0.20
    åŃĺåľ¨çļĦ
    -0.19
    åıªè¦ģæľī
    -0.19
    çľĭäºĨçľĭ
    -0.19
    [][
    -0.19
    å¦Ĥæŀľä¸įæĺ¯
    -0.18
    认è¯ĨåĪ°
    -0.18
    POSITIVE LOGITS
    ä¸ĩä¸Ģ
    0.33
    ëĿ¼ëıĦ
    0.26
    çªģ
    0.26
    åıijçĶŁ
    0.25
    çªģåıij
    0.24
    æľīä»»ä½ķ
    0.24
    éľĢè¦ģçĶ¨åĪ°
    0.23
    æŁIJ个
    0.23
    æĥħåĨµè¿Ľè¡Į
    0.23
    æŁIJä¸Ģ
    0.23
    Activations Density 0.057%

    No Known Activations