© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17242
    Prev
    Next
    INDEX
    Explanations

    Equality Act and protections

    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
    Negative Logits
    对åħ¶çľŁå®ŀ
    -0.23
    åĻ¨æĿIJ
    -0.23
    åıĸå¾Ĺ以åıĬ
    -0.20
     зим
    -0.20
    第ä¸ī代
    -0.19
     зак
    -0.19
    elic
    -0.19
     пеÑĢе
    -0.19
    upa
    -0.19
    Singleton
    -0.19
    POSITIVE LOGITS
    ä¿ĿæĬ¤
    0.24
    人身
    0.22
     grop
    0.22
    使人
    0.21
     protection
    0.21
    illion
    0.21
    åĴ
    0.20
     protections
    0.20
    essler
    0.20
    aisy
    0.20
    Activations Density 0.019%

    No Known Activations