© 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. 22-TRANSCODER-HP
    7. 98943
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     widening
    -0.28
     separately
    -0.28
     worsening
    -0.28
     Everywhere
    -0.27
     spokes
    -0.25
    ç¼Ł
    -0.25
    ä¸Ģåī¯
    -0.24
     LOCK
    -0.24
    spi
    -0.24
     individually
    -0.24
    POSITIVE LOGITS
    æĥ³è¦ģ
    0.27
    dimension
    0.26
    inky
    0.24
    åĴĮå¹³
    0.23
    qus
    0.23
     dimension
    0.23
    èļĢ
    0.23
    åľ¨æѤ
    0.23
    æ´¾
    0.23
    noopener
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.