© 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. 63820
    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
    .usage
    -0.26
    yled
    -0.25
     buttonText
    -0.25
    antal
    -0.25
     sentence
    -0.25
    åºķä¸ĭ
    -0.24
    usage
    -0.24
     roughly
    -0.23
    elor
    -0.23
    æİ¥ä¸ĭæĿ¥
    -0.23
    POSITIVE LOGITS
    èµŀåIJĮ
    0.26
    è¡Ĺ头
    0.26
    ä¿ĥ
    0.25
    导读
    0.25
     birth
    0.25
    è¿Ļ个è¡Įä¸ļ
    0.25
    èĵ¬
    0.24
    çĶŁæĹ¥
    0.24
     birthdays
    0.24
     birthday
    0.24
    Activations Density 32.524%

    No Known Activations

    This feature has no known activations.