© 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. 10570
    Prev
    Next
    INDEX
    Explanations

    resources provided by

    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
    ä¼´éļı
    -0.21
    rees
    -0.20
    åł°
    -0.19
    ATCH
    -0.19
     witnessing
    -0.18
    ancial
    -0.18
    åIJĮ
    -0.18
    blink
    -0.18
    atch
    -0.17
    edin
    -0.17
    POSITIVE LOGITS
    logg
    0.20
    tex
    0.19
    -Smith
    0.18
    èİĴ
    0.18
    æĿĵ
    0.18
    FER
    0.18
    åij¨åĽĽ
    0.18
    梳
    0.17
    urent
    0.17
    fix
    0.17
    Activations Density 0.003%

    No Known Activations