© 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. 3193
    Prev
    Next
    INDEX
    Explanations

    structure and repair

    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
    Negative Logits
    folk
    -0.27
    票
    -0.26
    æ±Ĥ
    -0.25
     glimpse
    -0.25
     shy
    -0.25
     downs
    -0.24
     Äijấu
    -0.24
    .Depth
    -0.24
    åľ¨åIJĮä¸Ģ
    -0.24
     autoplay
    -0.23
    POSITIVE LOGITS
    建çŃijæĿIJæĸĻ
    0.40
     structures
    0.38
    repair
    0.37
    .structure
    0.36
     structure
    0.35
    structure
    0.35
    Repair
    0.34
    STRUCT
    0.33
     Structures
    0.32
    Structure
    0.32
    Activations Density 0.239%

    No Known Activations