© 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. 22127
    Prev
    Next
    INDEX
    Explanations

    Parentheses and commas

    np_max-act · gemini-2.0-flash
    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
    æĢł
    -0.29
    为主
    -0.28
     butcher
    -0.27
    åĽĽåij¨
    -0.27
    æĻĸ
    -0.26
    å¤ļå¹´
    -0.25
    è¿ĩå¤ļ
    -0.25
    æĸĹ
    -0.24
    ming
    -0.24
    _concat
    -0.24
    POSITIVE LOGITS
    ForResource
    0.28
    vla
    0.28
    ogr
    0.25
    ä¼ģä¸ļæıIJä¾Ľ
    0.25
    CardBody
    0.24
    åį¡çīĩ
    0.24
     washer
    0.24
    Series
    0.23
    edef
    0.23
    edList
    0.23
    Activations Density 0.009%

    No Known Activations