© 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. 20-TRANSCODER-HP
    7. 62870
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sutton
    -0.27
    å¯Ŀ
    -0.26
     attend
    -0.25
    =output
    -0.25
     attending
    -0.25
    /latest
    -0.25
    绪
    -0.25
    æĥ«
    -0.25
    hunt
    -0.24
    ноÑģ
    -0.24
    POSITIVE LOGITS
    quia
    0.32
    éŨæĪ·
    0.26
    Projection
    0.26
    porto
    0.26
    ãĥıãĤ¦
    0.26
    身为
    0.26
    stands
    0.25
    ihan
    0.25
     Alger
    0.24
    ||↵
    0.24
    Activations Density 19.336%

    No Known Activations

    This feature has no known activations.