© 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. 12044
    Prev
    Next
    INDEX
    Explanations

    mixed content, numbers, and questions

    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
    æİ°
    -0.21
    allet
    -0.21
    ogn
    -0.20
    ium
    -0.20
     imper
    -0.20
     saturation
    -0.19
    ç²¾ç¥ŀ
    -0.19
    åĽŀéģ¿
    -0.19
     patron
    -0.19
    -p
    -0.19
    POSITIVE LOGITS
    æīŃ转
    0.21
    åħ¶æ¬¡æĺ¯
    0.21
    ä¹ĭ举
    0.20
    ÑĢÑĥг
    0.20
    ä»ħ代表
    0.20
    è¾ķ
    0.20
    åŀĭåı·
    0.19
    æľºåŀĭ
    0.19
    ç½ijç«Ļé¦ĸ页
    0.19
     pornô
    0.19
    Activations Density 0.052%

    No Known Activations