© 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. 20-TRANSCODER-HP
    7. 141413
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izedName
    -0.31
    isé
    -0.28
    izes
    -0.26
    astery
    -0.26
    ize
    -0.25
    å¼ĢéĺĶ
    -0.25
    isas
    -0.25
    çĬĬ
    -0.25
     brow
    -0.24
    ized
    -0.24
    POSITIVE LOGITS
    INET
    0.26
    壽
    0.26
    寿
    0.26
    ä¿Ŀè´¹
    0.24
    odate
    0.24
     Shaun
    0.24
    æĹ©çĤ¹
    0.24
    .${
    0.23
    <!
    0.23
    amb
    0.23
    Activations Density 49.472%

    No Known Activations

    This feature has no known activations.