© 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. 88380
    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
    reen
    -0.27
    ipers
    -0.27
     Harmon
    -0.25
    åģı
    -0.25
    Band
    -0.25
    WND
    -0.25
     Ones
    -0.25
    {{
    -0.24
    ened
    -0.24
     Bands
    -0.24
    POSITIVE LOGITS
    usions
    0.27
    AILS
    0.25
     concentrates
    0.25
    emplates
    0.25
    ilage
    0.24
    åľ°å¤Ħ
    0.24
    解åĨ³æĸ¹æ¡Ī
    0.24
    kinson
    0.24
    vironment
    0.24
    .preferences
    0.24
    Activations Density 0.277%

    No Known Activations

    This feature has no known activations.