© 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. 128990
    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
    家éķ¿ä»¬
    -0.30
     surpr
    -0.28
    ocial
    -0.28
    åĽļ
    -0.26
    社ä¼ļæķĪçĽĬ
    -0.25
    ä¸ŀ
    -0.25
    alar
    -0.25
    社ä¼ļåĮĸ
    -0.25
     Tup
    -0.24
    bara
    -0.24
    POSITIVE LOGITS
     IRA
    0.31
    è§Ĥ
    0.29
    **↵
    0.29
     trans
    0.28
    æµĵ
    0.28
     gum
    0.26
    ï¼Ł↵
    0.26
    ]**
    0.25
    úa
    0.24
     Sources
    0.24
    Activations Density 7.174%

    No Known Activations

    This feature has no known activations.