© 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. 15925
    Prev
    Next
    INDEX
    Explanations

    launch and promotion

    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
    æºľ
    -0.22
    åĩĢåĮĸ
    -0.21
    ourses
    -0.19
    æ»ĭ润
    -0.18
    ä¿Ŀåģ¥
    -0.18
    诨
    -0.18
    妥åĸĦ
    -0.17
     бÑİ
    -0.17
     Sequ
    -0.17
    _que
    -0.17
    POSITIVE LOGITS
    ä½ľèĢħæľ¬äºº
    0.22
    æ¥Ķ
    0.21
    毯
    0.21
    åıijè¡Į
    0.21
    launch
    0.20
    æIJº
    0.20
    æĸ°æ¬¾
    0.20
     launch
    0.20
     promotion
    0.20
    åıijåĶ®
    0.19
    Activations Density 0.083%

    No Known Activations