© 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. 142366
    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
    rá
    -0.28
    :Array
    -0.28
    èIJ¥ä¸ļ
    -0.26
    arr
    -0.26
     Arr
    -0.25
    bre
    -0.25
    åħ¨æĹ¥
    -0.25
    -Disposition
    -0.24
    	arr
    -0.24
     deter
    -0.24
    POSITIVE LOGITS
     strips
    0.27
    EMU
    0.26
     masters
    0.26
    æĸ¹ãģ¯
    0.26
    еб
    0.24
    avy
    0.23
     Masters
    0.23
    ırım
    0.23
    è¿«
    0.23
    èĸħ
    0.23
    Activations Density 6.535%

    No Known Activations

    This feature has no known activations.