© 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. 13728
    Prev
    Next
    INDEX
    Explanations

    legal roles and author/narrator

    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
    大å±Ģ
    -0.23
    å®ĥ们
    -0.22
    åĩºæĿ¥çļĦ
    -0.21
    人们
    -0.20
    人们çļĦ
    -0.20
    ä¸ĭæĿ¥çļĦ
    -0.19
    åIJĦèĩªçļĦ
    -0.19
    æĪij们çļĦ
    -0.19
    åŀ£
    -0.18
    turn
    -0.18
    POSITIVE LOGITS
    åıĬåħ¶
    0.23
    æĺ¯ä¸Ģä½į
    0.21
    oser
    0.19
    亲身
    0.19
     nữ
    0.19
    åĴĮ社ä¼ļ
    0.18
    åĴĮä»ĸçļĦ
    0.18
    çļĦæĥħ绪
    0.18
    ufs
    0.18
     dap
    0.18
    Activations Density 0.177%

    No Known Activations