© 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. 38538
    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
     Sup
    -0.28
    ç¥ŀ
    -0.27
    sh
    -0.27
    Sh
    -0.27
    Sup
    -0.27
    ÙĬÙĪ
    -0.27
     Arch
    -0.27
     Sh
    -0.27
    åľŁ
    -0.27
    |
    -0.26
    POSITIVE LOGITS
    scription
    0.29
    otine
    0.29
    nika
    0.28
     richest
    0.28
    onacci
    0.28
     undes
    0.26
    inals
    0.26
    主é¢ĺæķĻèĤ²
    0.26
     +=↵
    0.26
    lename
    0.26
    Activations Density 1.089%

    No Known Activations

    This feature has no known activations.