© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13412
    Prev
    Next
    INDEX
    Explanations

    consecutive days, weeks, times, years, wins

    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
    Not in Any Lists

    No Comments

    Negative Logits
    fully
    -0.26
     Preserve
    -0.20
    åģıåģı
    -0.18
    åħ¶ä¸Ńä¸Ģ个
    -0.18
    åįģ足
    -0.18
    ãģıãĤĮ
    -0.17
    amp
    -0.17
    æĹħ游度åģĩ
    -0.17
    é©¿ç«Ļ
    -0.17
    isto
    -0.16
    POSITIVE LOGITS
    ively
    0.26
    idad
    0.21
    -minded
    0.20
    utivo
    0.19
    stration
    0.19
    -looking
    0.19
    ity
    0.18
    vely
    0.18
    cy
    0.18
    èĢĮåıĪ
    0.18
    Activations Density 0.023%

    No Known Activations