© 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. 1833
    Prev
    Next
    INDEX
    Explanations

    quantifying time durations or extreme points

    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
    ä¸Ģ件
    -0.29
    -my
    -0.23
     beautifully
    -0.23
    设计æĸ¹æ¡Ī
    -0.23
     curses
    -0.23
     curious
    -0.23
     fascinating
    -0.22
     vulgar
    -0.22
    è¿ĻäºĽä¸ľè¥¿
    -0.22
    æĪijçĽ¸ä¿¡
    -0.22
    POSITIVE LOGITS
    èµ·ä¼ı
    0.28
     indices
    0.24
    åĪĨæŀIJå¸Ī
    0.23
     trimest
    0.23
    è¡°éĢĢ
    0.23
     volatility
    0.23
    åıįå¼¹
    0.23
    unist
    0.23
     trend
    0.23
    åĬłæģ¯
    0.22
    Activations Density 0.019%

    No Known Activations