© 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. 62571
    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
    leton
    -0.31
    æ¡Ī
    -0.30
    Ĥ¬
    -0.28
    æĿĥ
    -0.27
    æłĩ
    -0.26
     strengthened
    -0.25
    å®ļ
    -0.25
    å¢ŀéĩı
    -0.25
    umn
    -0.25
    udos
    -0.24
    POSITIVE LOGITS
    creen
    0.28
    ACA
    0.27
    atories
    0.25
    ä¸Ģç§Ĵ
    0.25
     Disclosure
    0.24
    NDER
    0.23
    anza
    0.23
    athy
    0.23
    _dependencies
    0.23
    AccountId
    0.23
    Activations Density 10.103%

    No Known Activations

    This feature has no known activations.