© 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. 90330
    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
    æľŁåĨħ
    -0.30
    ê¶Į
    -0.27
    urg
    -0.27
    ắn
    -0.25
     Loop
    -0.25
    éĸĵ
    -0.25
    _cycle
    -0.25
    Remaining
    -0.25
    污æŁĵçī©
    -0.24
    循çݯ
    -0.24
    POSITIVE LOGITS
    ä¹¾åĿ¤
    0.27
     Gol
    0.27
    :url
    0.26
    é¹Ĭ
    0.26
     separat
    0.25
    (loader
    0.25
    å¾ģéĽĨ
    0.25
    .gradient
    0.25
    bff
    0.24
    dq
    0.24
    Activations Density 1.200%

    No Known Activations

    This feature has no known activations.