© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1041
    Prev
    Next
    INDEX
    Explanations

    NHS health services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    Club
    -0.29
    .Company
    -0.27
    为客æĪ·
    -0.27
    Interest
    -0.26
    Company
    -0.25
    æįķæįī
    -0.25
    çĪ±å¥½èĢħ
    -0.25
    è¯ģ书
    -0.25
     Company
    -0.24
    款å¼ı
    -0.24
    POSITIVE LOGITS
     NHS
    0.33
     budgets
    0.31
     hospital
    0.31
    绣çŃ¹
    0.30
     hospitals
    0.30
    æĶ¹éĿ©åıijå±ķ
    0.28
    åĮ»çĸĹ
    0.28
     healthcare
    0.28
     Wales
    0.28
     subsystem
    0.27
    Activations Density 0.084%

    No Known Activations