© 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. 35-TRANSCODER-HP
    7. 40537
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¥Ĺè£ħ
    -0.29
    walker
    -0.27
    æł¡å¤ĸ
    -0.27
    å½Ģ
    -0.26
    ç§ijæĻ®
    -0.26
    çݯçIJĥ
    -0.26
    apa
    -0.25
    æĿ¿åĿĹ
    -0.25
    被æĬĵ
    -0.25
    é£ij
    -0.24
    POSITIVE LOGITS
    /demo
    0.28
    -mouth
    0.26
     favourites
    0.25
     Trades
    0.25
    /private
    0.24
    URN
    0.24
    hu
    0.24
     fib
    0.24
     forgotten
    0.24
    åºŃ
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.