© 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. 129366
    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
    Not in Any Lists

    No Comments

    Negative Logits
    .False
    -0.28
    arity
    -0.28
     dearly
    -0.27
    oster
    -0.27
    avia
    -0.26
    亮
    -0.26
    &_
    -0.25
    father
    -0.25
     Indigenous
    -0.25
    ogenic
    -0.25
    POSITIVE LOGITS
    å¿Ĺ
    0.27
    kop
    0.25
    iffin
    0.25
    JKLM
    0.24
    é¢Ĩä¼ļ
    0.24
    -feed
    0.23
    .jsp
    0.23
    ç»°
    0.23
    FK
    0.23
    istle
    0.23
    Activations Density 20.024%

    No Known Activations

    This feature has no known activations.