© 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. 30-TRANSCODER-HP
    7. 94910
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    stre
    -0.29
    路桥
    -0.28
    æļĦ
    -0.27
     impro
    -0.26
    oll
    -0.26
    logged
    -0.25
    è¿ĻæĿ¡è·¯
    -0.25
    liÄŁini
    -0.25
    hell
    -0.25
    osi
    -0.24
    POSITIVE LOGITS
    åĴĮå¹³
    0.32
    æīģ
    0.27
    æĹĭ转
    0.27
    çŃ¹éĽĨ
    0.27
     Scale
    0.27
    åĩ¹
    0.26
    ç¢į
    0.26
    anches
    0.25
    .onView
    0.25
     Rotation
    0.25
    Activations Density 0.937%

    No Known Activations

    This feature has no known activations.