© 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. 23384
    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
    ug
    -0.30
    ↵↵
    -0.28
     re
    -0.27
    ward
    -0.27
    åīª
    -0.26
     Was
    -0.26
     Design
    -0.26
    arus
    -0.26
     Days
    -0.26
     Ref
    -0.26
    POSITIVE LOGITS
    leton
    0.31
    西äºļ
    0.28
    unci
    0.26
    ycastle
    0.26
    -bedroom
    0.26
    еÑģÑĤ
    0.26
     moduleId
    0.26
    微信群
    0.26
    MDB
    0.25
     hoops
    0.25
    Activations Density 0.021%

    No Known Activations

    This feature has no known activations.