© 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. 140546
    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
    uve
    -0.32
    UNE
    -0.27
    失è°ĥ
    -0.26
    UIL
    -0.26
    éĬ
    -0.25
    åºĶçĶ¨
    -0.25
    è¿ĻæĿ¡
    -0.24
    ouis
    -0.24
    _countries
    -0.24
    å°ıå°ı
    -0.24
    POSITIVE LOGITS
     magn
    0.25
     departing
    0.24
     Griffin
    0.24
    uras
    0.23
    igham
    0.23
     Vo
    0.23
    $↵
    0.22
     chim
    0.22
    ossier
    0.22
     bait
    0.22
    Activations Density 66.988%

    No Known Activations

    This feature has no known activations.