© 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. 10361
    Prev
    Next
    INDEX
    Explanations

    permanent, long-term, durable

    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
    corn
    -0.22
    istik
    -0.21
    åħ³æ³¨åº¦
    -0.21
    说èĩªå·±
    -0.21
    é¢IJ
    -0.21
     Bloody
    -0.21
    å°ıæŶåīį
    -0.20
    å°Ĩèĩªå·±çļĦ
    -0.20
    MAND
    -0.19
    表éĿ¢ä¸Ĭ
    -0.19
    POSITIVE LOGITS
    æ°¸ä¹ħ
    0.45
    éķ¿æķĪæľºåĪ¶
    0.35
     perman
    0.35
     permanently
    0.34
     permanent
    0.34
    ä»ĬåIJİ
    0.33
    permanent
    0.32
    éķ¿è¿ľ
    0.31
    éķ¿ä¹ħ
    0.31
     lasting
    0.30
    Activations Density 0.177%

    No Known Activations