© 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. 64842
    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
     deflate
    -0.32
     stil
    -0.28
     realize
    -0.26
    ä¸Ģæīĭ
    -0.26
    è¿Ļä¹Īåģļ
    -0.25
    åķī
    -0.24
    integral
    -0.24
    ialized
    -0.24
     realizing
    -0.24
    èĦijæµ·ä¸Ń
    -0.23
    POSITIVE LOGITS
    é½
    0.28
    thing
    0.25
    ä½ĵ温
    0.25
    ród
    0.24
    èĦ±
    0.24
    è´Łè½½
    0.24
     bır
    0.24
    说ä¸įåĩº
    0.24
    zy
    0.24
     Erdogan
    0.24
    Activations Density 29.429%

    No Known Activations

    This feature has no known activations.