© 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. 12746
    Prev
    Next
    INDEX
    Explanations

    woman, life, fame, single

    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
    æѤ类
    -0.27
    åīĸ
    -0.22
    å¼ij
    -0.21
    è¯ļæĦı
    -0.21
    çĩĥæ²¹
    -0.20
    atform
    -0.20
    çĩĥçħ¤
    -0.20
    æĭŁå®ļ
    -0.20
    ä¸įè¿ľ
    -0.20
    çĥ
    -0.20
    POSITIVE LOGITS
    æ¯ı天
    0.21
    maintenance
    0.20
     oc
    0.20
     days
    0.20
    è¿Ļ件äºĭ
    0.19
    æ¯ıä¸Ģ天
    0.19
    å¾Īå¤ļäºĭæĥħ
    0.19
    å°ıäºĭ
    0.19
    åĪ«äºº
    0.18
     trans
    0.18
    Activations Density 0.109%

    No Known Activations