© 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. 129296
    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
    Not in Any Lists

    No Comments

    Negative Logits
    scoped
    -0.28
    quel
    -0.27
     Salvador
    -0.26
     quali
    -0.25
    bdb
    -0.25
    _ACL
    -0.24
    AMED
    -0.24
    ldb
    -0.24
    #$
    -0.24
    enses
    -0.24
    POSITIVE LOGITS
    imon
    0.31
    Concern
    0.29
    åĵ¨
    0.28
     sammen
    0.27
    oriously
    0.27
    itably
    0.24
     aracı
    0.24
     Manit
    0.24
     awaiting
    0.24
     cot
    0.24
    Activations Density 1.303%

    No Known Activations

    This feature has no known activations.