© 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. 2732
    Prev
    Next
    INDEX
    Explanations

    be completed or given

    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
    beeld
    -0.24
    å·²ç»ıæľīäºĨ
    -0.23
    éģŃåıĹ
    -0.22
    åıijçİ°èĩªå·±
    -0.22
    å°±æĺ¯è¿Ļæł·
    -0.22
    太å¤ļçļĦ
    -0.22
    论述
    -0.22
    çݯçIJĥ
    -0.22
     criticised
    -0.22
    åħ»æĪIJ
    -0.21
    POSITIVE LOGITS
     either
    0.27
    贯穿
    0.24
    either
    0.24
    æĶ¾åĪ°
    0.24
    à¸Ļำà¹Ħà¸Ľ
    0.24
    igraph
    0.24
    æĶ¾åľ¨
    0.23
    ä¾
    0.23
    éĽĨä¸Ńåľ¨
    0.23
    èķ¤
    0.23
    Activations Density 0.120%

    No Known Activations