© 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. 3428
    Prev
    Next
    INDEX
    Explanations

    Ridge Mountain jazz GRASS monitor

    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
    zelf
    -0.23
    ä¸įåıĬ
    -0.23
     Wolff
    -0.22
    裤åŃIJ
    -0.22
    æľīæľŁ
    -0.22
    pts
    -0.22
    ldata
    -0.22
    oen
    -0.22
    atas
    -0.21
    ä¸ĢåįĬ
    -0.21
    POSITIVE LOGITS
    åIJĮå¿ĥ
    0.24
    åľ°åĮº
    0.23
    æ·±è¿ľ
    0.23
     Boolean
    0.23
     Tea
    0.23
    _DEFINE
    0.23
    çĶŁäº§åĬĽ
    0.23
    IFT
    0.23
     Seas
    0.22
     craftsmanship
    0.22
    Activations Density 0.001%

    No Known Activations