© 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. 22-TRANSCODER-HP
    7. 88741
    Prev
    Next
    INDEX
    Explanations

    Medical studies and risks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Ĭ¶æĢģ
    -0.28
    )=(
    -0.26
     /\
    -0.26
    æľīæŶåĢĻ
    -0.26
    æĢ»ä¼ļ
    -0.26
    ãģ«ãģªãĤĭãģ¨
    -0.24
    æĪĽ
    -0.24
    OMET
    -0.24
    /op
    -0.24
     annum
    -0.23
    POSITIVE LOGITS
     reports
    0.31
     research
    0.29
     Reports
    0.28
    Reports
    0.28
    Report
    0.27
     studies
    0.27
    æĬ¥åijĬ
    0.26
    .report
    0.26
     report
    0.26
     Report
    0.26
    Activations Density 0.001%

    No Known Activations