© 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. 30-TRANSCODER-HP
    7. 94922
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ¼Ĩ
    -0.25
    IEW
    -0.25
     already
    -0.24
     lev
    -0.23
    åIJ
    -0.23
    trusted
    -0.23
    çļĦ主é¢ĺ
    -0.23
    è¿Ļ家åħ¬åı¸
    -0.23
     markdown
    -0.23
     immediately
    -0.23
    POSITIVE LOGITS
    atus
    0.28
     Moments
    0.27
    kker
    0.27
    gar
    0.26
    frared
    0.26
    éĺ´éĺ³
    0.26
     bóng
    0.24
     Library
    0.24
    (types
    0.24
     absl
    0.24
    Activations Density 0.102%

    No Known Activations

    This feature has no known activations.