© 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. 88295
    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
    _slope
    -0.26
    Ticks
    -0.25
    /Gate
    -0.24
    [++
    -0.24
     GÅĤ
    -0.24
    tier
    -0.24
    ÑĢоÑģл
    -0.24
    tre
    -0.24
    è¿Ļ份
    -0.23
    ipop
    -0.23
    POSITIVE LOGITS
    èĬ±å¼Ģ
    0.27
     foundation
    0.27
    .foundation
    0.25
     discord
    0.24
     ׼ף
    0.24
    å¾Ĺ天
    0.24
    åıĤ
    0.24
    enz
    0.23
    æħĮ
    0.23
    Found
    0.23
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.