© 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. 31-TRANSCODER-HP
    7. 17799
    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
    Negative Logits
    éħĭ
    -0.28
    uien
    -0.28
     dim
    -0.27
    é³ŀ
    -0.26
    æį
    -0.26
    (dim
    -0.25
    .dim
    -0.25
    otte
    -0.24
    åģ¿è¿ĺ
    -0.24
    /items
    -0.24
    POSITIVE LOGITS
    iffs
    0.29
    DEL
    0.29
    neys
    0.27
    庵
    0.27
    çĽĬ
    0.27
     publicity
    0.26
    ToRemove
    0.25
    rell
    0.25
    INCREMENT
    0.24
    inz
    0.24
    Activations Density 22.136%

    No Known Activations

    This feature has no known activations.