© 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. 22267
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ublish
    -0.28
     ul
    -0.25
     Commissioner
    -0.25
     vá»įng
    -0.25
    .responseText
    -0.25
    äl
    -0.24
    æģ°å¥½
    -0.24
    lius
    -0.23
    绳
    -0.23
     ogs
    -0.23
    POSITIVE LOGITS
    éĵ¶
    0.24
     portfolios
    0.24
    {k
    0.24
    todos
    0.24
    <b
    0.24
    boards
    0.24
     {!!
    0.23
    kos
    0.23
    æĬķ票
    0.23
    åĵŃ
    0.23
    Activations Density 0.000%

    No Known Activations