© 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. 90229
    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
    å°±åºĶ该
    -0.27
    erals
    -0.27
    irectory
    -0.26
     instances
    -0.26
    agens
    -0.26
    ajor
    -0.25
    ages
    -0.24
    etails
    -0.24
     instance
    -0.24
    -interest
    -0.24
    POSITIVE LOGITS
     dik
    0.26
     desn
    0.26
    ADED
    0.26
    isen
    0.25
    åļ·
    0.24
    лÑĥ
    0.24
     Picasso
    0.24
     IPCC
    0.24
    æĶ¹åıĺäºĨ
    0.24
    bjerg
    0.23
    Activations Density 4.183%

    No Known Activations

    This feature has no known activations.