© 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. 88100
    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
    rchive
    -0.27
     conform
    -0.26
    ä¸įåĩº
    -0.24
    åŃ¦æľŁ
    -0.24
    aris
    -0.24
    æĺ¯åIJ¦ä¼ļ
    -0.24
    elier
    -0.23
    aminer
    -0.23
     orth
    -0.23
    (pd
    -0.23
    POSITIVE LOGITS
    anela
    0.26
    ç´ł
    0.25
    hydr
    0.25
    èĮħåı°
    0.25
    iban
    0.25
     particular
    0.24
    ima
    0.24
    èµı
    0.24
    æĦŁæ¿Ģ
    0.24
    pps
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.