© 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. 3292
    Prev
    Next
    INDEX
    Explanations

    parenthesized clarifications or alternate names

    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
    æĦıè¯Ĩ
    -0.25
    è´
    -0.24
    -Free
    -0.23
    å°±æĺ¯ä¸Ģ个
    -0.21
    ading
    -0.20
    å¾IJ
    -0.20
    Ĭ¶
    -0.20
    perf
    -0.20
    æ»´
    -0.20
    æľºåĪ¶
    -0.20
    POSITIVE LOGITS
    ispers
    0.27
    åIJİèĢħ
    0.23
    blas
    0.22
     ware
    0.22
     parts
    0.21
     possibly
    0.21
    wav
    0.21
     Pall
    0.21
     ruth
    0.21
    parts
    0.20
    Activations Density 0.157%

    No Known Activations