© 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. 10353
    Prev
    Next
    INDEX
    Explanations

    scores and 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
     dev
    -0.21
    egrator
    -0.20
     UM
    -0.19
    åı¦ä¸Ģä½į
    -0.19
     $('<
    -0.19
    åħ¥
    -0.18
    å¥ĸåĬ±
    -0.18
     Mare
    -0.18
    èĩªä»İ
    -0.18
    .gms
    -0.18
    POSITIVE LOGITS
    _columns
    0.20
    èĮĦåŃIJ
    0.20
    ä¸įåĪ©
    0.20
    ä¸į太好
    0.19
    _strings
    0.18
    romatic
    0.18
    uela
    0.18
     اÙĦØŃدÙĬØ«
    0.18
    计è¾ĥ
    0.18
    _titles
    0.18
    Activations Density 0.007%

    No Known Activations