© 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. 106822
    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
    Occurred
    -0.30
    _hooks
    -0.28
    åŃķ
    -0.27
    ä½ĵä¼ļåĪ°
    -0.25
    ialized
    -0.24
    icity
    -0.24
     ******************************************************************************/↵↵
    -0.24
    _INITIALIZ
    -0.24
    pty
    -0.23
    åıijè´¢
    -0.23
    POSITIVE LOGITS
     pri
    0.29
     Multi
    0.28
     exclusion
    0.27
     Main
    0.26
    bung
    0.26
    åı°
    0.26
     multi
    0.25
     Hard
    0.24
    Multi
    0.24
    urus
    0.24
    Activations Density 33.096%

    No Known Activations

    This feature has no known activations.