© 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. 9867
    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
    示èĮĥ
    -0.28
    erman
    -0.27
     chú
    -0.26
    çļĦè®°å¿Ĩ
    -0.25
    demo
    -0.24
     nhỼ
    -0.24
     poll
    -0.24
    大家åı¯ä»¥
    -0.24
     demo
    -0.23
    itect
    -0.23
    POSITIVE LOGITS
    å¾ĹçĽĬ
    0.26
    lef
    0.25
    alc
    0.25
    tif
    0.24
    çªĴæģ¯
    0.24
    iddy
    0.24
    pend
    0.24
    aler
    0.24
    缯
    0.23
     Wat
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.