© 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. 30-TRANSCODER-HP
    7. 96975
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    YPD
    -0.29
    perience
    -0.26
     discovers
    -0.25
     filament
    -0.25
     weaker
    -0.25
    浯
    -0.24
    oward
    -0.24
    åIJ¦
    -0.24
    rif
    -0.23
    RoutingModule
    -0.23
    POSITIVE LOGITS
    æŶéĹ´ä¸º
    0.28
    esar
    0.27
    urat
    0.27
    è´Ŀ
    0.26
    深度
    0.25
    .rawValue
    0.25
    sonian
    0.25
    å¡«åħħ
    0.24
    -fill
    0.24
     hoop
    0.24
    Activations Density 0.104%

    No Known Activations

    This feature has no known activations.