© 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. 107316
    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
    jos
    -0.25
    herit
    -0.25
    itos
    -0.24
    usch
    -0.24
    积åĪĨ
    -0.23
    æĭŃ
    -0.23
    stroy
    -0.23
     McDonald
    -0.23
    COMPLETE
    -0.22
    Äĩe
    -0.22
    POSITIVE LOGITS
    奶
    0.27
    èĦ±ç¦»
    0.27
    åĬŁ
    0.26
     pivot
    0.26
    aris
    0.24
     notÃŃcia
    0.24
     cast
    0.24
    cast
    0.24
    acific
    0.24
     pob
    0.23
    Activations Density 13.554%

    No Known Activations

    This feature has no known activations.