© 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. 107638
    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
    丰å¯ĮçļĦ
    -0.28
    丰å¯Į
    -0.28
    åĨįçĶŁèĥ½æºIJ
    -0.27
    åįıä¼ļä¼ļéķ¿
    -0.26
    Carthy
    -0.24
     Beverage
    -0.24
    ä¸įè´Ł
    -0.24
     scissors
    -0.24
    积æŀģéħįåIJĪ
    -0.23
    广大
    -0.23
    POSITIVE LOGITS
    æµĨ
    0.27
    å¢ĥ
    0.27
    æľ«
    0.26
    åĵĹ
    0.26
    å±ħ
    0.26
    èĨĤ
    0.25
    æĺ¼
    0.25
    /doc
    0.25
     cv
    0.25
    _refs
    0.25
    Activations Density 5.677%

    No Known Activations

    This feature has no known activations.