© 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. 151222
    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
    çļĦçĶ·äºº
    -0.27
    loaded
    -0.27
    igated
    -0.26
    Loaded
    -0.25
     reloading
    -0.25
    ConnectionFactory
    -0.25
     loader
    -0.24
    xfc
    -0.24
    roc
    -0.24
    ream
    -0.24
    POSITIVE LOGITS
    deserialize
    0.25
    yal
    0.25
    |M
    0.24
     ais
    0.24
    çľīæ¯Ľ
    0.24
     Graphic
    0.24
     Organic
    0.24
    ]|
    0.24
    imore
    0.23
     Ãĸl
    0.23
    Activations Density 5.007%

    No Known Activations

    This feature has no known activations.