© 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. 21940
    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
    æĤĮ
    -0.28
    马æĿ¥
    -0.26
    thood
    -0.25
     stor
    -0.24
    urga
    -0.24
    aroo
    -0.24
    å¢ŀ
    -0.24
     Indies
    -0.23
    èĢ³è¾¹
    -0.23
     collaborations
    -0.23
    POSITIVE LOGITS
     bets
    0.27
    æ²Ľ
    0.26
    åIJ¯çĶ¨
    0.25
    æ§Ľ
    0.24
    .removeItem
    0.24
    estro
    0.24
    åIJijåīį
    0.24
    ewood
    0.23
     pulver
    0.23
     outnumber
    0.23
    Activations Density 0.000%

    No Known Activations