© 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. 18-TRANSCODER-HP
    7. 88304
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    磶
    -0.28
    pac
    -0.27
    磷
    -0.26
     purely
    -0.25
    cho
    -0.25
     elseif
    -0.24
    eld
    -0.24
    Leading
    -0.24
    ä¼ļéķ¿
    -0.24
     responded
    -0.24
    POSITIVE LOGITS
    erson
    0.26
    ÙĤب
    0.26
    ä¸įä¸ĭ
    0.25
    ķĮ
    0.25
    åĺĺ
    0.24
    å¤ĩ注
    0.24
    agnet
    0.24
    æĮĤåľ¨
    0.24
     france
    0.24
    ipc
    0.23
    Activations Density 1.126%

    No Known Activations

    This feature has no known activations.