© 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. 62609
    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
    ORM
    -0.27
    wagon
    -0.27
    ĵį
    -0.26
     suc
    -0.24
    avel
    -0.24
     ign
    -0.24
    umat
    -0.23
     Suc
    -0.23
    åľ°æłĩ
    -0.23
    ä¹ĺ
    -0.23
    POSITIVE LOGITS
    極
    0.27
    ä¸ŃæľŁ
    0.26
    åĮĹæĸ¹
    0.25
    arp
    0.24
    arked
    0.24
     Shell
    0.24
    ustering
    0.24
    ëĥ¥
    0.24
    aran
    0.24
    åIJ¬äºĨ
    0.23
    Activations Density 1.095%

    No Known Activations

    This feature has no known activations.