© 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. 88094
    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
    arcer
    -0.30
     keyed
    -0.28
    æľ¬æĬ¥è®°èĢħ
    -0.26
    ocity
    -0.26
    صر
    -0.25
     key
    -0.24
    ENU
    -0.24
    gni
    -0.24
    个æĢ§
    -0.24
    KeyName
    -0.24
    POSITIVE LOGITS
    é£İåIJ¹
    0.26
    èĩ¨
    0.26
     legitimately
    0.26
    shipping
    0.25
    å´İ
    0.25
    ButtonClick
    0.25
    èĩ´
    0.24
    èĢ»
    0.24
    SEND
    0.23
    æĬĹçĶŁç´ł
    0.23
    Activations Density 69.810%

    No Known Activations

    This feature has no known activations.