© 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. 20-TRANSCODER-HP
    7. 131142
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     afterwards
    -0.30
     relevance
    -0.27
    że
    -0.27
    bones
    -0.27
     ÙĪÙĦÙĥ
    -0.26
    ude
    -0.24
     FRIEND
    -0.24
    究竣
    -0.24
     between
    -0.24
     Afterwards
    -0.24
    POSITIVE LOGITS
     Fairy
    0.28
    æł¼æŀĹ
    0.28
     Moor
    0.25
    __),
    0.25
    avax
    0.24
    å¤ĸ交éĥ¨
    0.24
    .âĢ¢
    0.24
     Publi
    0.24
    侪
    0.24
    =index
    0.24
    Activations Density 36.858%

    No Known Activations

    This feature has no known activations.