© 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. 19-TRANSCODER-HP
    7. 9516
    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
    Negative Logits
    æĪĺçķ¥æĢ§
    -0.29
    odem
    -0.28
    nger
    -0.28
    åIJį人
    -0.26
    ooks
    -0.25
    å½ĵ代
    -0.25
    iques
    -0.24
    tau
    -0.24
    ÏĦ
    -0.24
    ng
    -0.24
    POSITIVE LOGITS
    atre
    0.26
    ypy
    0.25
    _EOF
    0.24
    ç¡®
    0.23
    .Mutable
    0.23
    atri
    0.23
    æĽ³
    0.23
    é£ŁæĿIJ
    0.23
    ITERAL
    0.23
    imately
    0.23
    Activations Density 0.047%

    No Known Activations

    This feature has no known activations.