© 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. 149165
    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
    è·Ŀ
    -0.28
     infr
    -0.27
     pret
    -0.26
    éĽĨä½ĵç»ıæµİ
    -0.24
    è·Ŀ离
    -0.24
    .ol
    -0.23
     fair
    -0.23
     insider
    -0.23
    è±ķ
    -0.23
     thinly
    -0.23
    POSITIVE LOGITS
     Rate
    0.31
    rate
    0.29
     Delivery
    0.27
    éĢŁçİĩ
    0.27
     Available
    0.27
     Accuracy
    0.27
    åŁł
    0.27
    screen
    0.27
    orna
    0.26
    Rate
    0.26
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.