© 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. 129030
    Prev
    Next
    INDEX
    Explanations

    Locations

    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
     yanı
    -0.29
    è¯Ģ
    -0.27
    åįĥå¹´
    -0.27
    ensburg
    -0.25
    hare
    -0.25
    第äºĮ个
    -0.24
    ippo
    -0.24
    红楼
    -0.23
    hiba
    -0.23
     اÙĦآخر
    -0.23
    POSITIVE LOGITS
    omo
    0.27
    çļĦåIJĦç§į
    0.26
    iless
    0.25
    iw
    0.25
    æľīå¾ħ
    0.24
    _bel
    0.24
    æĴĤ
    0.24
     bel
    0.23
     Conditioning
    0.23
    大大å°ıå°ı
    0.23
    Activations Density 71.738%

    No Known Activations