© 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. 11659
    Prev
    Next
    INDEX
    Explanations

    emigrated, arrived, came

    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
    çĸı导
    -0.22
    åĮĻ
    -0.22
    åľºæīĢ
    -0.21
    äºĪ以
    -0.21
    åĨħ马
    -0.20
    çľĭ书
    -0.20
    æľŁåĨħ
    -0.19
    èµ·æĿ¥äºĨ
    -0.19
    åĪĨæĺİ
    -0.19
    æĶ¾åģĩ
    -0.19
    POSITIVE LOGITS
    æĬµè¾¾
    0.23
    æĿ¥åĪ°
    0.22
    带çĿĢ
    0.21
    åħ¥å¢ĥ
    0.21
    é¦ĸæī¹
    0.20
    çķĻåѦçĶŁ
    0.20
    into
    0.20
    åĪ°è¾¾
    0.20
    æIJº
    0.20
     arrivals
    0.20
    Activations Density 0.053%

    No Known Activations