© 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. 9026
    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
    á»ģu
    -0.28
    ên
    -0.26
    iren
    -0.25
    -pre
    -0.25
    éħį
    -0.25
    --
    -0.24
    cao
    -0.24
    æĹłæĦı
    -0.24
    è·³
    -0.24
    .pred
    -0.24
    POSITIVE LOGITS
    OPSIS
    0.27
    稳妥
    0.26
     maxHeight
    0.25
    .pageY
    0.25
     speedy
    0.24
    åIJł
    0.24
    éľľ
    0.24
    .easy
    0.24
     beste
    0.24
    æĹ©çĤ¹
    0.24
    Activations Density 0.854%

    No Known Activations

    This feature has no known activations.