© 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. 15737
    Prev
    Next
    INDEX
    Explanations

    wealth and riches

    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
    åIJįé¢Ŀ
    -0.23
    çļĩåŃIJ
    -0.20
    åĪĩ
    -0.19
    çĶ¨å·¥
    -0.19
    roupon
    -0.19
    æ¡£
    -0.18
    åİĦ
    -0.18
    è´¹çĶ¨
    -0.18
    arb
    -0.18
    亲
    -0.18
    POSITIVE LOGITS
     wealth
    0.26
    è´¢å¯Į
    0.25
    inherit
    0.24
    åĩĢèµĦ产
    0.24
    ç½®ä¸ļ
    0.23
    财产
    0.23
    åŃĺéĩı
    0.23
    éĽĦåİļ
    0.20
     inheritance
    0.20
    åĩĢåĢ¼
    0.20
    Activations Density 0.016%

    No Known Activations