© 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. 90130
    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
    drops
    -0.27
     `\
    -0.26
    æıĸ
    -0.26
    alto
    -0.25
    rex
    -0.25
    ç«Ļç«ĭ
    -0.24
     &$
    -0.24
    eldo
    -0.24
     cul
    -0.24
    ÄĻp
    -0.23
    POSITIVE LOGITS
    ake
    0.31
    åı¯è¡Į
    0.27
    ấu
    0.25
    åºŁ
    0.25
     feeds
    0.25
    è·ijäºĨ
    0.25
    anchor
    0.24
     feed
    0.24
    è§Ĥä¼Ĺ
    0.24
    åı¯ä¿¡
    0.24
    Activations Density 0.371%

    No Known Activations

    This feature has no known activations.