© 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. 131005
    Prev
    Next
    INDEX
    Explanations

    Programming questions

    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
     Españ
    -0.27
    é¢Ħè§ģ
    -0.27
    âĪ
    -0.27
    åĴ¨è¯¢æľįåĬ¡
    -0.27
    avity
    -0.25
    æł·å¼ı
    -0.25
     Cran
    -0.25
    让大家
    -0.25
    èµĬ
    -0.24
    borrow
    -0.24
    POSITIVE LOGITS
    转åĮĸ为
    0.58
    -to
    0.50
    转æį¢
    0.46
    转åıĺ为
    0.44
    转åĮĸ
    0.42
     converting
    0.42
     convert
    0.41
     converted
    0.41
    转
    0.41
    convert
    0.40
    Activations Density 80.445%

    No Known Activations