© 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. 25-TRANSCODER-HP
    7. 109433
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     caval
    -0.27
     debates
    -0.26
     bikes
    -0.26
     judges
    -0.25
     motorcycles
    -0.25
    -Requested
    -0.25
     preferring
    -0.24
    ONT
    -0.24
     sacks
    -0.24
    æĦı大
    -0.24
    POSITIVE LOGITS
    ç½®
    0.27
    èĦ¯
    0.27
    ูà¹Ī
    0.26
    -et
    0.26
    hole
    0.25
    åIJŃ
    0.25
     pud
    0.24
    举æĸ¹è´¢å¯Į
    0.24
    æ±īæĹı
    0.24
    vo
    0.24
    Activations Density 0.252%

    No Known Activations

    This feature has no known activations.