© 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. 64772
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    <<<<<<<<
    -0.31
    æĢ»éĥ¨
    -0.29
    åīĮ
    -0.28
    UGE
    -0.28
    åĹ£
    -0.25
    欲
    -0.24
     Drugs
    -0.24
    ãĤīãģĦ
    -0.24
     Clarke
    -0.24
    åľ¨åħ¨åĽ½
    -0.24
    POSITIVE LOGITS
    olf
    0.26
     $($
    0.25
    obody
    0.25
    anford
    0.24
     indebted
    0.24
     REP
    0.24
    宵
    0.24
    atore
    0.24
    yntax
    0.23
    phabet
    0.23
    Activations Density 0.318%

    No Known Activations