© 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. 13549
    Prev
    Next
    INDEX
    Explanations

    rights, sovereignty, freedom, liberty

    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
    è¿Ľå±ķæĥħåĨµ
    -0.20
    åIJĪéĢĤçļĦ
    -0.19
    éĽ¢ãĤĮ
    -0.19
    åħ·æľīèī¯å¥½
    -0.19
    ä¸Ģåī¯
    -0.18
    è¿Ļç§įæĸ¹å¼ı
    -0.18
    ä¸ŃåĽ½åĪ¶éĢł
    -0.18
    åľ°å½¢
    -0.18
    çļĦåĵģçīĮ
    -0.18
    麾
    -0.18
    POSITIVE LOGITS
     freedoms
    0.26
     liberties
    0.23
     rights
    0.22
    éļIJç§ģ
    0.20
    iox
    0.19
     dil
    0.19
    axter
    0.19
    çłº
    0.19
    寸
    0.19
    INAL
    0.18
    Activations Density 0.012%

    No Known Activations