© 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. 90105
    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
    fell
    -0.27
    afi
    -0.27
    andum
    -0.27
    _esc
    -0.26
    HM
    -0.26
    çĶ°åĽŃ
    -0.25
    ac
    -0.25
    ç§ij
    -0.24
    èµĭ
    -0.24
    ä¸įèµ·
    -0.24
    POSITIVE LOGITS
    .every
    0.29
    yclopedia
    0.27
    รà¸ģ
    0.27
    俯
    0.27
    \Builder
    0.27
    è¦ģä¹Ī
    0.25
    ãĤ¢ãĥĬ
    0.25
     competed
    0.25
    .Comparator
    0.25
     BÃŃ
    0.24
    Activations Density 0.959%

    No Known Activations

    This feature has no known activations.