© 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. 8298
    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
    _prediction
    -0.27
     Pompe
    -0.26
    åIJ¬åıĸ
    -0.25
    illance
    -0.25
    UrlParser
    -0.25
    -san
    -0.25
    çļĦåĽŀçŃĶ
    -0.25
    ky
    -0.24
    lice
    -0.24
    (/[
    -0.24
    POSITIVE LOGITS
    åIJĪæĪIJ
    0.30
    æį¢
    0.26
    说åĩº
    0.26
    åħį
    0.26
    latex
    0.25
    çĺª
    0.25
     riff
    0.24
    æĭ®
    0.24
     explodes
    0.24
    chied
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.