© 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. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142643
    Prev
    Next
    INDEX
    Explanations

    "after all"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    insky
    -0.30
    åģı
    -0.27
     dazu
    -0.26
    æľīåħ³
    -0.26
     permalink
    -0.24
    çļĦå½¢å¼ı
    -0.24
    ooter
    -0.24
    -marker
    -0.23
    mits
    -0.23
    å§Ķ
    -0.23
    POSITIVE LOGITS
    è¿Ļæīįæĺ¯
    0.27
    endir
    0.27
     sinus
    0.25
     Sin
    0.25
    etary
    0.24
    æĪijä»¬çŁ¥éģĵ
    0.24
    since
    0.24
     spectacular
    0.24
    erras
    0.23
    åģ¥åº·çļĦ
    0.23
    Activations Density 7.072%

    No Known Activations