© 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. 17048
    Prev
    Next
    INDEX
    Explanations

    Birmingham City

    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
    ting
    -0.21
    gram
    -0.18
    ç²ľ
    -0.17
    æĭ£
    -0.17
    ging
    -0.17
    ortion
    -0.17
    éŨåı£
    -0.17
    çĺ¾
    -0.16
    èĽı
    -0.16
    ary
    -0.16
    POSITIVE LOGITS
    abbage
    0.16
    wares
    0.16
    nett
    0.15
    æĬ¬å¤´
    0.15
     luáºŃt
    0.15
    iston
    0.15
     Wolver
    0.15
    halt
    0.15
    andas
    0.15
    .hm
    0.14
    Activations Density 0.006%

    No Known Activations