© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12411
    Prev
    Next
    INDEX
    Explanations

    social welfare conditions

    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
    ration
    -0.21
    ç²¾ç¥ŀæĸĩæĺİ
    -0.20
    è¢į
    -0.20
    åĭĥåĭĥ
    -0.20
    æ²IJ
    -0.19
    éĩįè¦ģåĨħ容
    -0.19
    轫
    -0.19
    èĵĬ
    -0.19
    æĴº
    -0.18
    责任åĪ¶
    -0.18
    POSITIVE LOGITS
    æŃ£ä¹ī
    0.23
     justice
    0.21
    æī¶è´«
    0.20
    akah
    0.19
    -friendly
    0.18
     &
    0.18
     whom
    0.18
    æľī两ç§į
    0.18
     injustice
    0.18
    justice
    0.18
    Activations Density 0.009%

    No Known Activations