© 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. 24-TRANSCODER-HP
    7. 149373
    Prev
    Next
    INDEX
    Explanations

    United Kingdom

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Pulitzer
    -0.33
    ä¸Ńç¾İ
    -0.32
     NOAA
    -0.32
     Caj
    -0.31
     Milwaukee
    -0.30
     Purdue
    -0.30
     Poe
    -0.30
     Rivera
    -0.30
    braska
    -0.29
     Guam
    -0.29
    POSITIVE LOGITS
     £
    0.78
    èĭ±åĽ½
    0.77
    £
    0.69
     UK
    0.69
     Britain
    0.68
    èĭ±åľĭ
    0.65
    伦æķ¦
    0.65
    èĭ±æł¼åħ°
    0.65
     Yorkshire
    0.64
    èĭ±éķij
    0.64
    Activations Density 4.987%

    No Known Activations