© 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. 58517
    Prev
    Next
    INDEX
    Explanations

    say "countries"

    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
     Achie
    -0.29
    åIJĦåĮº
    -0.27
    ;charset
    -0.27
    ective
    -0.26
    axon
    -0.25
    (pages
    -0.25
    å¤ĸåĽ½äºº
    -0.25
    Achie
    -0.25
    .awt
    -0.24
    unic
    -0.24
    POSITIVE LOGITS
    bot
    0.28
    ãģį
    0.25
    çļĦæĸ¹å¼ıæĿ¥
    0.25
    */č↵
    0.25
    ä¼ģä¸ļ
    0.24
     boy
    0.24
    */č↵č↵
    0.24
    ers
    0.24
     boys
    0.24
    sWith
    0.24
    Activations Density 0.005%

    No Known Activations