© 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. 140734
    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
     reaff
    -0.25
    ushman
    -0.25
     Kendall
    -0.25
    -na
    -0.25
    (IConfiguration
    -0.25
     fizz
    -0.25
    åīĤ
    -0.24
    çĪ·
    -0.24
    象
    -0.24
    Agents
    -0.24
    POSITIVE LOGITS
    idity
    0.30
    asser
    0.25
    mony
    0.24
    ä¸Ģé¦ĸ
    0.24
    èŀįåIJĪ
    0.24
     Cruc
    0.23
    ä¸ĢåĪĩéĥ½
    0.23
    ohan
    0.23
    lim
    0.23
     reviewing
    0.23
    Activations Density 6.970%

    No Known Activations

    This feature has no known activations.