© 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. 27-TRANSCODER-HP
    7. 56483
    Prev
    Next
    INDEX
    Explanations

    mode

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ucer
    -0.31
     Barrett
    -0.26
    çĽı
    -0.26
    omen
    -0.25
    inds
    -0.24
     collapses
    -0.24
     neigh
    -0.24
    åIJĦçľģ
    -0.24
    æĭīæĸ¯
    -0.23
     posts
    -0.23
    POSITIVE LOGITS
     mode
    1.12
     Mode
    0.99
    模å¼ı
    0.96
    	mode
    0.93
    mode
    0.93
    .mode
    0.91
    Mode
    0.91
     modes
    0.91
    _mode
    0.90
    -mode
    0.85
    Activations Density 0.002%

    No Known Activations