© 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. 108795
    Prev
    Next
    INDEX
    Explanations

    Dates in news articles

    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
     Pistol
    -0.26
     requestOptions
    -0.25
    XE
    -0.25
    åį¿
    -0.24
    çIJĨ
    -0.23
    èļĤ
    -0.23
    enton
    -0.23
    媳
    -0.23
    å¤ı天
    -0.23
    .dis
    -0.23
    POSITIVE LOGITS
    ahrenheit
    0.28
    olest
    0.26
    encing
    0.25
    ç½ijé¦ĸ页
    0.25
    gue
    0.24
     Duck
    0.24
    EXPECTED
    0.24
    ertility
    0.24
    _predicted
    0.23
    ponder
    0.23
    Activations Density 4.921%

    No Known Activations