© 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. 10540
    Prev
    Next
    INDEX
    Explanations

    budget cuts

    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
    æķ£å¸ĥ
    -0.24
    éĵº
    -0.22
    глÑı
    -0.21
    éĭª
    -0.21
    轻微
    -0.20
    çļĦæĪIJåĬŁ
    -0.20
    ä»ij
    -0.20
     kull
    -0.20
    åĮĸè¿Ľç¨ĭ
    -0.20
    æĬĬæı¡
    -0.20
    POSITIVE LOGITS
    å¿į
    0.26
     funding
    0.25
    ç»ıè´¹
    0.24
    æĶ¯æĮģåĬĽåº¦
    0.22
    é¢Ħç®Ĺ
    0.22
    èµĦåĬ©
    0.21
    inx
    0.21
     budgets
    0.21
    yar
    0.20
     cuts
    0.20
    Activations Density 0.028%

    No Known Activations