© 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. 13863
    Prev
    Next
    INDEX
    Explanations

    prejudice and discrimination

    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
    ç¼¢
    -0.21
    çĪ½
    -0.21
    signals
    -0.20
    é©·
    -0.20
    æģº
    -0.19
    ç²¾éĢī
    -0.19
     suic
    -0.19
    AMP
    -0.18
    urre
    -0.18
    _signals
    -0.18
    POSITIVE LOGITS
    æѧè§Ĩ
    0.36
     prejud
    0.25
     prejudice
    0.24
     discrimination
    0.22
    æľīèī²
    0.22
    iscrimination
    0.20
    å«ī
    0.20
    å²IJ
    0.20
    对å¾ħ
    0.20
    ç§įæĹı
    0.20
    Activations Density 0.083%

    No Known Activations