© 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. 31-TRANSCODER-HP
    7. 18394
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stood
    -0.28
    åı¸
    -0.27
     onload
    -0.26
    åįģåŃĹ
    -0.26
    è¿IJ
    -0.25
     ÐľÐ¸Ð½
    -0.25
    йÑĤ
    -0.25
    åĵ®åĸĺ
    -0.24
     Strange
    -0.24
    éģĭ
    -0.24
    POSITIVE LOGITS
    rei
    0.28
    compet
    0.27
    渥
    0.25
    oses
    0.25
    hawk
    0.25
     sé
    0.24
    pet
    0.24
    workspace
    0.24
    ä¿¡æģ¯åħ¬å¼Ģ
    0.24
    åĪĬ
    0.23
    Activations Density 1.588%

    No Known Activations