© 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. 31-TRANSCODER-HP
    7. 19689
    Prev
    Next
    INDEX
    Explanations

    Names of people/places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ma
    -0.34
     Mae
    -0.32
    olta
    -0.32
    Ada
    -0.30
     mat
    -0.30
    mat
    -0.29
     Ed
    -0.28
    IDA
    -0.28
    pha
    -0.28
    erta
    -0.28
    POSITIVE LOGITS
    éĥİ
    0.28
    份
    0.27
    LAY
    0.27
     Bars
    0.27
    bars
    0.26
    åĢŁ
    0.26
    Bars
    0.25
    æŃ¥
    0.25
    alley
    0.25
    IPPING
    0.25
    Activations Density 21.237%

    No Known Activations