© 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. 24-TRANSCODER-HP
    7. 151419
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    #__
    -0.26
    acam
    -0.26
    çļĦè¿ĩç¨ĭ
    -0.25
    rogate
    -0.24
    UBLE
    -0.24
    说æĺİ书
    -0.24
    TION
    -0.24
    upert
    -0.24
     protagon
    -0.24
    íĮĮíĬ¸
    -0.23
    POSITIVE LOGITS
    âĪĴ
    0.28
    (lib
    0.26
    astr
    0.25
    pieces
    0.25
    åĽ½æľīä¼ģä¸ļ
    0.24
     Libraries
    0.24
    lib
    0.24
    Lib
    0.24
    Storm
    0.24
     Astr
    0.24
    Activations Density 1.028%

    No Known Activations

    This feature has no known activations.