© 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. 23-TRANSCODER-HP
    7. 25569
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ↵     ↵
    -0.26
    'C
    -0.25
    æĸ°åįİç½ij
    -0.25
    olo
    -0.25
    å¼
    -0.25
    oth
    -0.24
    æĶ¯çº¿
    -0.24
    'R
    -0.24
    "https
    -0.24
     Spears
    -0.23
    POSITIVE LOGITS
     {*
    0.28
     Quite
    0.25
     {.
    0.24
     vinc
    0.24
    imports
    0.24
    affer
    0.23
     slid
    0.23
     neck
    0.23
     tied
    0.23
     Bucket
    0.23
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.