© 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. 142641
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    utter
    -0.27
    ika
    -0.27
     Gamb
    -0.26
    isten
    -0.26
    ogo
    -0.26
    iOS
    -0.26
     Force
    -0.25
     heated
    -0.25
    -null
    -0.25
    ita
    -0.25
    POSITIVE LOGITS
     Journalism
    0.26
    (dc
    0.25
     sting
    0.23
     ÑģÑĤали
    0.23
    åľ¨è¿Ļæĸ¹éĿ¢
    0.23
    enze
    0.23
     Democr
    0.23
     advantage
    0.23
    nze
    0.23
    è¯ķ
    0.22
    Activations Density 1.893%

    No Known Activations

    This feature has no known activations.