© 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. 142533
    Prev
    Next
    INDEX
    Explanations

    Initial/beginning

    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
    bz
    -0.27
    /ns
    -0.27
    BREAK
    -0.26
    å¯ħ
    -0.26
     Uber
    -0.25
    lius
    -0.25
    羣åģĩ
    -0.24
     Require
    -0.24
    åIJŁ
    -0.24
     BET
    -0.24
    POSITIVE LOGITS
    æĪij个人
    0.28
    æľ¬ç½ijç«Ļ
    0.27
     []).
    0.26
     fid
    0.25
    åľ°ä¸Ń
    0.24
    é¦ĸ
    0.24
    å¤§åľ°
    0.23
    åħĪè¿ĽçļĦ
    0.23
    åľ°çIJĥ
    0.23
     personal
    0.23
    Activations Density 52.272%

    No Known Activations