© 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. 142547
    Prev
    Next
    INDEX
    Explanations

    Defining characteristics and descriptions

    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
    oya
    -0.29
    渡
    -0.28
     chá»ĵng
    -0.26
    è¿Ļä¹Īä¹ħ
    -0.26
    人æŃ»äº¡
    -0.26
    itional
    -0.26
    cai
    -0.25
    太è¿ĩ
    -0.25
     Rise
    -0.25
    .Pop
    -0.24
    POSITIVE LOGITS
    compact
    0.28
    åĹĴ
    0.27
     drained
    0.27
    []{
    0.24
    ä¸īä½į
    0.24
    ấp
    0.24
    auer
    0.24
     Levin
    0.24
     cracked
    0.24
     Lever
    0.24
    Activations Density 18.406%

    No Known Activations