© 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. 149136
    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
    OfWork
    -0.28
    详
    -0.27
    nea
    -0.26
    åı¦å¤ĸä¸Ģ个
    -0.25
    inci
    -0.25
    æľº
    -0.25
    izers
    -0.25
    è§ģåĪ°
    -0.23
    Me
    -0.23
     Ro
    -0.23
    POSITIVE LOGITS
    postData
    0.26
     Patton
    0.25
    çļĦä¾ĭåŃIJ
    0.25
     Jain
    0.24
    çIJĥè¿·
    0.24
    WA
    0.24
     debating
    0.24
    wä
    0.24
     cannons
    0.24
    å°ıå§IJ
    0.23
    Activations Density 0.160%

    No Known Activations

    This feature has no known activations.