© 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. 142530
    Prev
    Next
    INDEX
    Explanations

    Spanish/Portuguese/German

    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
     opener
    -0.26
    -friendly
    -0.26
    upro
    -0.26
    ä¸Ģå¥Ĺ
    -0.25
    ijk
    -0.25
     encaps
    -0.25
    aria
    -0.25
    涵
    -0.25
    -head
    -0.25
    ôt
    -0.24
    POSITIVE LOGITS
     Scrolls
    0.27
    ï¼ļ%
    0.25
     nxt
    0.25
    Partial
    0.24
    Ĺı
    0.24
    ookie
    0.24
    _LVL
    0.23
    /dom
    0.23
     Bucks
    0.23
     Tencent
    0.23
    Activations Density 9.046%

    No Known Activations