© 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. 17831
    Prev
    Next
    INDEX
    Explanations

    and

    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
    çľĭæ³ķ
    -0.29
     meters
    -0.28
    åŀļ
    -0.26
    assage
    -0.26
    dek
    -0.25
    åŁºéĩijä¼ļ
    -0.25
    å¥ĭæĸĹ缮æłĩ
    -0.25
    ynet
    -0.25
    عبر
    -0.24
     ther
    -0.24
    POSITIVE LOGITS
    åŃĶ
    0.26
     learner
    0.26
    employer
    0.25
    cliffe
    0.25
    .leading
    0.24
    åį´è¢«
    0.24
     Cli
    0.23
    itelist
    0.23
     trail
    0.23
    isher
    0.23
    Activations Density 0.017%

    No Known Activations