© 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. 142583
    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
    avis
    -0.24
    (Table
    -0.24
     KC
    -0.24
    idian
    -0.24
    se
    -0.23
    åIJİå¤ĩ
    -0.23
     buds
    -0.23
    å®¡æŁ¥
    -0.23
    utorial
    -0.23
     nightclub
    -0.22
    POSITIVE LOGITS
     Degrees
    0.27
    isti
    0.27
    æĸ°å¨ĺ
    0.26
    建设åĴĮ
    0.25
     Dynamics
    0.25
    .Physics
    0.25
    _male
    0.24
    alking
    0.24
    è¯ŃéŁ³
    0.24
    -duration
    0.24
    Activations Density 24.095%

    No Known Activations

    This feature has no known activations.