© 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. 11287
    Prev
    Next
    INDEX
    Explanations

    gifts and occasions

    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¸īæĿ¡
    -0.25
     Platt
    -0.21
    ét
    -0.20
     yok
    -0.20
    Platform
    -0.20
    æīĢè°ĵçļĦ
    -0.20
    akk
    -0.20
    两æĿ¡
    -0.19
    æīĢè°ĵ
    -0.19
     fav
    -0.19
    POSITIVE LOGITS
    éĹ®åĢĻ
    0.25
    ç¥Ŀç¦ı
    0.21
    绿åŁİ
    0.21
    ç¥Ŀè´º
    0.21
    亲æĥħ
    0.21
    çĭ¬ä¸ĢæĹłäºĮ
    0.21
    missive
    0.20
    åħ³çĪ±
    0.20
    称åij¼
    0.20
    æ·¡æ·¡çļĦ
    0.20
    Activations Density 0.030%

    No Known Activations