© 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. 106962
    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
    èĭĮ
    -0.25
     ya
    -0.25
    angen
    -0.25
    lık
    -0.24
     Ya
    -0.24
     schools
    -0.24
    rale
    -0.24
    ucc
    -0.24
    ya
    -0.23
    Ya
    -0.23
    POSITIVE LOGITS
     european
    0.28
    榴
    0.27
    ogie
    0.26
     provisional
    0.26
     fiss
    0.26
    æĹ¶ä»£çļĦ
    0.26
     originals
    0.25
    å±ij
    0.25
    ALA
    0.25
    .tt
    0.25
    Activations Density 4.685%

    No Known Activations

    This feature has no known activations.