© 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. 20-TRANSCODER-HP
    7. 129329
    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
     known
    -0.28
     Shelby
    -0.27
    ANGED
    -0.27
    èĴ¸
    -0.26
    -known
    -0.25
     com
    -0.25
    _tolerance
    -0.25
    åIJİæŀľ
    -0.24
    ç¼Ŀ
    -0.24
    hetto
    -0.23
    POSITIVE LOGITS
    ç§ijåѦåıijå±ķ
    0.31
    airo
    0.27
    ORTH
    0.27
    模æĭŁ
    0.27
    .hot
    0.26
    ÙĬÙĥا
    0.26
    åIJ¹
    0.25
    鲨
    0.25
    马æĿ¥
    0.25
    åºĶ该å¦Ĥä½ķ
    0.25
    Activations Density 13.074%

    No Known Activations

    This feature has no known activations.