© 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. 17808
    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
    é¥Ń
    -0.27
    Under
    -0.26
    under
    -0.26
    åIJ¦
    -0.25
    usta
    -0.25
     Neg
    -0.25
     altında
    -0.25
     market
    -0.25
    iram
    -0.25
     ['$
    -0.24
    POSITIVE LOGITS
    订
    0.28
    æĢİä¹Īä¼ļ
    0.27
    梣
    0.26
    _WP
    0.26
    ään
    0.26
    loquent
    0.26
    yo
    0.26
    åħ¨åİ¿
    0.25
     fragmentation
    0.25
    CPP
    0.25
    Activations Density 0.130%

    No Known Activations