© 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. 17257
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
    -0.24
    -0.21
    ’
    -0.20
     ’
    -0.20
     Rip
    -0.19
    èĢĮåİ»
    -0.19
     crest
    -0.18
    æ´ª
    -0.18
    OS
    -0.18
    å¹ķ
    -0.18
    POSITIVE LOGITS
    essed
    0.23
    ä»·åĢ¼éĵ¾
    0.20
    thouse
    0.19
     lows
    0.18
    _phys
    0.17
    ä¸įéĶĪ
    0.17
    iants
    0.17
    æľīæķĪæľŁ
    0.17
    ilen
    0.17
    enties
    0.17
    Activations Density 0.045%

    No Known Activations