© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56581
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    被æī§è¡Į
    -0.27
     infinitely
    -0.27
    <void
    -0.26
     myster
    -0.25
    ä½Ĩä»ĸ们
    -0.24
    ä¸İä¼Ĺ
    -0.24
    ç´§æī£
    -0.24
     extensively
    -0.24
    被害人
    -0.24
    acket
    -0.23
    POSITIVE LOGITS
     navigator
    0.29
    è¾°
    0.28
     jav
    0.27
    isser
    0.24
    aron
    0.24
    navigator
    0.23
     android
    0.23
    åįĴ
    0.23
    ä¸ŃåİŁ
    0.23
    âĭĦ
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.