© 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. 129114
    Prev
    Next
    INDEX
    Explanations

    Progression, Change

    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
    ä¹Łå°±æĺ¯
    -0.32
    桶
    -0.28
    artz
    -0.28
    ikhail
    -0.25
     eds
    -0.24
    ç´¢åıĸ
    -0.24
     puerto
    -0.23
    丧
    -0.23
    åĪĨæ³Į
    -0.23
    æĹ¢è¦ģ
    -0.23
    POSITIVE LOGITS
     and
    0.34
    Fore
    0.31
     Fore
    0.31
    åıĬ
    0.27
     vÃł
    0.27
     Hum
    0.27
    Hum
    0.26
    .Areas
    0.26
    ,copy
    0.26
     и
    0.26
    Activations Density 69.676%

    No Known Activations