© 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. 12-TRANSCODER-HP
    7. 22054
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Earth
    -0.27
     ancest
    -0.26
    IBE
    -0.25
     sez
    -0.25
    neutral
    -0.24
    reak
    -0.24
    earn
    -0.24
    subcategory
    -0.23
    ccione
    -0.23
    STREAM
    -0.23
    POSITIVE LOGITS
    å®ļäºĨ
    0.29
    éĥİ
    0.28
    å¼¥
    0.27
    æ²»çĸĹæĸ¹æ³ķ
    0.26
    é¡¿
    0.25
    ä¿®æŃ£
    0.25
    éłĵ
    0.24
    ague
    0.24
    kel
    0.23
    igi
    0.23
    Activations Density 0.000%

    No Known Activations