© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130726
    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
    æıIJ款
    -0.27
    (distance
    -0.25
    expanded
    -0.24
    Crud
    -0.24
     bef
    -0.24
    åı¯
    -0.24
    expense
    -0.23
     sl
    -0.23
    ä¼łæī¿
    -0.23
    paren
    -0.23
    POSITIVE LOGITS
    gons
    0.33
    kaza
    0.27
    ynchronously
    0.25
    ALA
    0.25
    ä¸Ńå¿ĥåŁİå¸Ĥ
    0.24
    olesale
    0.24
    .digital
    0.23
    дов
    0.23
     kull
    0.23
     revel
    0.23
    Activations Density 6.185%

    No Known Activations

    This feature has no known activations.