© 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. 20-TRANSCODER-HP
    7. 108681
    Prev
    Next
    INDEX
    Explanations

    Comparisons/medical studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ¦Ĥçİĩ
    -0.26
    çĻ½éĵ¶
    -0.26
    ĤŃ
    -0.25
    veyor
    -0.25
    çĿĢæīĭ
    -0.24
     nameof
    -0.24
    æĮ¤
    -0.24
    æĮĩçĿĢ
    -0.24
    å¼Ħ
    -0.24
    Regarding
    -0.24
    POSITIVE LOGITS
    æŀ¢
    0.29
     cape
    0.28
    opaque
    0.26
    H
    0.26
     Pend
    0.26
    opsis
    0.25
    åģı
    0.25
    ä¹ĭåĨħ
    0.25
    odos
    0.25
     vulnerable
    0.24
    Activations Density 46.088%

    No Known Activations