© 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. 64680
    Prev
    Next
    INDEX
    Explanations

    and or comma

    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
    ught
    -0.26
    åĮħæĭ¬
    -0.25
    rade
    -0.25
     departed
    -0.25
    åįĥ
    -0.24
    åĮĹæĸ¹
    -0.24
    ä¸įæĥľ
    -0.24
     McMahon
    -0.24
    imiter
    -0.24
    masters
    -0.24
    POSITIVE LOGITS
    ç¥Ł
    0.28
    ç½ijæ°ij
    0.27
    书éĿ¢
    0.26
    éªļ
    0.26
    ercise
    0.23
    odo
    0.23
    mono
    0.23
     press
    0.23
    æĺ¯æľĢ好çļĦ
    0.23
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    0.23
    Activations Density 16.547%

    No Known Activations