© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12624
    Prev
    Next
    INDEX
    Explanations

    medical emergencies and concern

    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
    ä¸Ģç¬Ķ
    -0.21
    tempts
    -0.20
    ä¸Ģéģĵ
    -0.20
    kip
    -0.20
    çŀ¿
    -0.19
    ullet
    -0.19
    odore
    -0.19
    óg
    -0.18
    angible
    -0.18
    vip
    -0.18
    POSITIVE LOGITS
    æĢ¥æķij
    0.26
    æķijåĬ©
    0.21
    常è¯Ĩ
    0.20
    Immediate
    0.19
    åij¼
    0.19
    æĭ¯
    0.19
    åį±
    0.19
     emergencies
    0.18
    Wrapped
    0.18
    åijĬ
    0.18
    Activations Density 0.002%

    No Known Activations