© 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. 32-TRANSCODER-HP
    7. 40832
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     SOL
    -0.28
    äºĴéĢļ
    -0.27
    OLL
    -0.27
     sol
    -0.27
    uck
    -0.26
     principalTable
    -0.25
    hest
    -0.25
    æľīæľºç»ĵåIJĪ
    -0.25
    andre
    -0.25
    UserService
    -0.25
    POSITIVE LOGITS
    头
    0.31
    éłŃ
    0.28
    bies
    0.27
    yun
    0.26
    é¾Ļ头
    0.26
     Äijầu
    0.25
     bets
    0.24
    caled
    0.24
    æĬĵ
    0.24
    å¼Ģå¥ĸ
    0.23
    Activations Density 0.000%

    No Known Activations