© 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. 88132
    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
    éŀ®
    -0.31
    èį£
    -0.27
    INS
    -0.26
    æĻºæħ§
    -0.25
    ynchronized
    -0.25
    çĶ¨äºº
    -0.25
    äºij
    -0.24
    .codehaus
    -0.24
    .intellij
    -0.23
    åĽłåħ¶
    -0.23
    POSITIVE LOGITS
    MLElement
    0.30
    gency
    0.27
    entar
    0.26
    PBS
    0.25
     neighb
    0.25
    Skeleton
    0.24
    éĶı
    0.24
    åĮĿ
    0.24
    对æĸ¹
    0.24
    hips
    0.24
    Activations Density 0.207%

    No Known Activations

    This feature has no known activations.