© 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. 64874
    Prev
    Next
    INDEX
    Explanations

    Code and 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
    ysize
    -0.26
     SHR
    -0.24
    esti
    -0.23
    ulls
    -0.23
    poi
    -0.23
    ä¼°
    -0.23
    atta
    -0.23
    éĢıæĺİ
    -0.23
    ysz
    -0.23
     settlement
    -0.23
    POSITIVE LOGITS
    ä¸Ģç»ı
    0.33
    ationToken
    0.26
    aye
    0.26
    åIJĥè¿ĩ
    0.25
     newcomers
    0.25
     times
    0.25
     bol
    0.24
    ä»°
    0.24
    ç¾¹
    0.24
     adaptations
    0.24
    Activations Density 63.418%

    No Known Activations