© 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. 11239
    Prev
    Next
    INDEX
    Explanations

    paragraph breaks

    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
    订éĺħ
    -0.22
     subscribed
    -0.19
    é£İéĩĩ
    -0.19
    çľĭ
    -0.18
    ãģķãģ¾
    -0.18
    scatter
    -0.18
    æĭĽèģĺä¿¡æģ¯
    -0.17
     subscribing
    -0.17
     scand
    -0.17
    å¹³è¡Į
    -0.17
    POSITIVE LOGITS
    åķĦ
    0.20
    tat
    0.19
    vit
    0.18
    æĺ¯ä¸Ģéĥ¨
    0.18
    гоÑĢод
    0.18
     Lar
    0.18
    illo
    0.18
    hoff
    0.17
    åĽŀ头
    0.17
    累累
    0.17
    Activations Density 0.003%

    No Known Activations