© 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. 10503
    Prev
    Next
    INDEX
    Explanations

    charged, arrested, guilty

    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
    æł¸å¿ĥåĮº
    -0.23
    è¯Ŀè¯ŃæĿĥ
    -0.20
    å«¡
    -0.20
    raft
    -0.19
    ünd
    -0.18
    èļĵ
    -0.18
    èĩªåıij
    -0.18
    鹬
    -0.18
    indi
    -0.18
    æŃ¼
    -0.17
    POSITIVE LOGITS
     Grat
    0.20
     hoop
    0.19
    .spy
    0.19
     Dzi
    0.19
    åĪĨåŃIJ
    0.19
    elen
    0.18
     Growing
    0.18
     former
    0.18
    fel
    0.18
    ä»ij
    0.17
    Activations Density 0.049%

    No Known Activations