© 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. 63525
    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
    uco
    -0.28
    ä¸Ģå®ļçļĦ
    -0.25
    æīį
    -0.25
    icom
    -0.24
     agents
    -0.24
    edi
    -0.24
    viders
    -0.24
     toxic
    -0.23
    ece
    -0.23
    levision
    -0.23
    POSITIVE LOGITS
    arter
    0.28
    åĢĺ
    0.26
    æ±ŁåĮº
    0.26
    客
    0.24
    yme
    0.24
     prere
    0.23
     Cher
    0.23
    umd
    0.23
     bund
    0.23
     <",
    0.23
    Activations Density 2.063%

    No Known Activations

    This feature has no known activations.