© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2702
    Prev
    Next
    INDEX
    Explanations

    win-win situation

    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
    å¾Īæĸ¹ä¾¿
    -0.25
     separate
    -0.24
    ubern
    -0.23
     sympathetic
    -0.23
    åĽŀäºĭ
    -0.23
    å¤ļç§įå½¢å¼ı
    -0.23
    otine
    -0.23
    ëĮĵ
    -0.23
    主è¦ģåĨħ容
    -0.22
     trope
    -0.22
    POSITIVE LOGITS
     customer
    0.47
    为客æĪ·
    0.45
    ä¼ģä¸ļåıijå±ķ
    0.44
    客æĪ·
    0.44
    ç»ıèIJ¥çIJĨ念
    0.44
    ä¼ģä¸ļçļĦ
    0.41
     customers
    0.41
    æĪIJåĬŁ
    0.40
    客æĪ·çļĦ
    0.40
    åħ¨ä½ĵåijĺå·¥
    0.40
    Activations Density 0.096%

    No Known Activations