© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8362
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owy
    -0.28
    oub
    -0.26
     lug
    -0.24
     reviewer
    -0.24
    çļĦåĽŀçŃĶ
    -0.23
    chedules
    -0.23
    stringstream
    -0.23
    éĹ´çļĦ
    -0.23
     reviewers
    -0.23
    /*@
    -0.23
    POSITIVE LOGITS
    åij½
    0.32
    .php
    0.28
     rele
    0.28
    .html
    0.28
     HTML
    0.24
    decode
    0.24
     Longitude
    0.24
     tri
    0.23
    plit
    0.23
    icia
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.