© 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. 11333
    Prev
    Next
    INDEX
    Explanations

    gala, benefit, or function events

    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
    ä¸į解
    -0.19
    è½®åĽŀ
    -0.19
    sel
    -0.19
    hood
    -0.18
    æ²¥
    -0.18
    ä¸į好
    -0.17
    åģļçļĦ
    -0.17
    lings
    -0.17
     tir
    -0.16
    è¾Ĩ车
    -0.16
    POSITIVE LOGITS
    éĹ¨ç¥¨
    0.20
    -winning
    0.20
    æļ¨
    0.19
    浪漫
    0.19
    缮æłĩ
    0.18
     Cobra
    0.18
    룸
    0.18
     اÙĦتط
    0.17
    禳
    0.17
    AndGet
    0.17
    Activations Density 0.005%

    No Known Activations