© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3077
    Prev
    Next
    INDEX
    Explanations

    events described by when

    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
    æĺ¯ä¸įæĺ¯
    -0.24
    æµģåĬ¨æĢ§
    -0.23
    æ³ķåĪĻ
    -0.23
    ernals
    -0.23
    主ä¹īæĢĿæĥ³
    -0.23
    èĢķèĢĺ
    -0.22
    è¡ĹåĮº
    -0.22
    缼åħ¸
    -0.22
    ipation
    -0.22
    é£İæĻ¯
    -0.21
    POSITIVE LOGITS
     suddenly
    0.26
    被åĪĹåħ¥
    0.25
    Suddenly
    0.23
     Suddenly
    0.23
    appa
    0.22
    ä»ĸåľ¨
    0.22
     Aux
    0.22
     sudden
    0.22
     firstly
    0.22
     Commander
    0.22
    Activations Density 0.041%

    No Known Activations