© 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. 62737
    Prev
    Next
    INDEX
    Explanations

    Code/technical documentation

    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
    åŀĭä¼ģä¸ļ
    -0.28
    ὶ
    -0.26
    .learn
    -0.26
    horn
    -0.25
    OUCH
    -0.25
    ระ
    -0.25
     nod
    -0.25
    Traits
    -0.23
    ç
    -0.23
    arine
    -0.23
    POSITIVE LOGITS
    æĮĩæĮ¥
    0.28
    æİĴ
    0.27
    ophage
    0.26
     ucz
    0.25
    æīĵ好
    0.24
    puts
    0.24
    åīª
    0.24
     drafting
    0.23
    ç¡IJ
    0.22
    andle
    0.22
    Activations Density 5.027%

    No Known Activations