© 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. 16583
    Prev
    Next
    INDEX
    Explanations

    before judges

    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
    iran
    -0.22
    ä»Ģä¹Īæł·çļĦ
    -0.20
    bean
    -0.20
    åĪ«
    -0.19
    eren
    -0.19
    anel
    -0.18
     Trick
    -0.18
    é¢Į
    -0.18
    ä¹īåĬ¡
    -0.18
    dÃŃ
    -0.18
    POSITIVE LOGITS
    åĽº
    0.18
    æĶ¯éħį
    0.18
     espec
    0.18
    еÑģÑĮ
    0.18
    ByKey
    0.17
    çĶ»çĶ»
    0.17
     Brilliant
    0.17
    гал
    0.17
    沿éĢĶ
    0.17
    漫éķ¿
    0.17
    Activations Density 0.026%

    No Known Activations