© 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. 7995
    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
    åIJĮæľŁ
    -0.27
     Greek
    -0.27
    sel
    -0.26
    Greek
    -0.25
    åIJį
    -0.25
    åģļæ³ķ
    -0.25
     looping
    -0.24
     fragment
    -0.24
     fle
    -0.24
    课å¤ĸ
    -0.24
    POSITIVE LOGITS
     chimney
    0.26
    abox
    0.26
    idth
    0.26
    çĶ°éĩİ
    0.25
     thirds
    0.25
    eries
    0.25
    éĩįè¦ģåİŁåĽł
    0.24
    handles
    0.24
    jee
    0.24
     Txt
    0.24
    Activations Density 0.195%

    No Known Activations

    This feature has no known activations.