© 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. 35-TRANSCODER-HP
    7. 38539
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĸģ
    -0.28
    .dp
    -0.27
    éļĪ
    -0.26
    licenses
    -0.25
     suffered
    -0.25
    Êģ
    -0.25
    强奸
    -0.23
    MW
    -0.23
    ;if
    -0.23
    :Event
    -0.23
    POSITIVE LOGITS
     lazy
    0.27
    çİĩ
    0.27
    èIJ½
    0.26
    ama
    0.24
     Lump
    0.24
    åģ¶
    0.24
    鼨
    0.24
     Fil
    0.24
    åīį
    0.24
     Bloom
    0.24
    Activations Density 0.743%

    No Known Activations

    This feature has no known activations.