© 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. 33-TRANSCODER-HP
    7. 52515
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ship
    -0.30
    met
    -0.29
     Met
    -0.28
     metab
    -0.27
    è¯Ŀ说
    -0.27
     Ships
    -0.26
     met
    -0.26
    error
    -0.26
    èĪ¹
    -0.25
     ships
    -0.25
    POSITIVE LOGITS
    outine
    0.28
    åĪĹ为
    0.27
    è´¢åĬĽ
    0.25
    ç¢ĵ
    0.24
    Tween
    0.24
    éra
    0.24
     DARK
    0.24
    æĬľãģij
    0.23
    [label
    0.23
    ÛĢ
    0.23
    Activations Density 0.045%

    No Known Activations

    This feature has no known activations.