© 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. 130266
    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
    ç¼ļ
    -0.24
    åīįçŀ»
    -0.24
    abcdefghijklmnopqrstuvwxyz
    -0.24
     kitt
    -0.23
     timeZone
    -0.23
    idot
    -0.23
    .toFloat
    -0.23
    ä¾ĭå¤ĸ
    -0.23
    hood
    -0.23
    sted
    -0.22
    POSITIVE LOGITS
    é²ľ
    0.28
     comparative
    0.27
     unle
    0.26
    åĬ£
    0.26
    urga
    0.26
    é¦Ļ
    0.24
    ä¸Ģå¼ł
    0.24
     Uses
    0.24
    éļIJ
    0.24
     hall
    0.24
    Activations Density 86.306%

    No Known Activations

    This feature has no known activations.