© 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. 142705
    Prev
    Next
    INDEX
    Explanations

    Common English language words

    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
    isko
    -0.30
     ÑįÑĤим
    -0.26
     !↵↵
    -0.25
    èĵ¼
    -0.24
    intendent
    -0.24
    hev
    -0.24
    澡
    -0.24
     Season
    -0.24
    æ»Ĥ
    -0.24
    对æѤ
    -0.23
    POSITIVE LOGITS
    ä¸Ģæĺ¯
    0.31
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.29
    ä¸Ģæĸ¹éĿ¢
    0.28
     firstly
    0.26
     zwar
    0.26
    åħĪæĺ¯
    0.26
    zego
    0.26
     unpaid
    0.25
    ire
    0.25
    åĶ±æŃĮ
    0.25
    Activations Density 57.443%

    No Known Activations