© 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. 130913
    Prev
    Next
    INDEX
    Explanations

    three

    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
     cop
    -0.27
    çļĦè·Ŀ离
    -0.27
    upy
    -0.25
    olis
    -0.25
    Distance
    -0.25
     undo
    -0.24
    ethyst
    -0.24
     rever
    -0.24
    ä»ŀ
    -0.24
    åĩĨ
    -0.23
    POSITIVE LOGITS
    å¹³åı°ä¸Ĭ
    0.26
    SPATH
    0.26
    åĩłåı¥
    0.26
    åĩºè·¯
    0.26
    YG
    0.25
    VG
    0.25
     smashing
    0.25
    主ä¹īèĢħ
    0.24
    æľ¬ç½ijç«Ļ
    0.24
    åįģåĩł
    0.24
    Activations Density 4.090%

    No Known Activations