© 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. 23-TRANSCODER-HP
    7. 23482
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ipes
    -0.29
     Against
    -0.28
     Furn
    -0.26
    acic
    -0.26
     McCabe
    -0.26
     scala
    -0.26
    opper
    -0.26
    ÑĨÑĥ
    -0.25
     Ñģка
    -0.24
    ÑĨа
    -0.24
    POSITIVE LOGITS
     PTS
    0.28
    åİŁåĪĽ
    0.28
    addock
    0.27
     twists
    0.26
    åĪĽæĸ°åıijå±ķ
    0.25
     snaps
    0.25
    åľ¨åIJĮä¸Ģ
    0.25
    çij¾
    0.24
     boredom
    0.24
    icum
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.