© 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. 62557
    Prev
    Next
    INDEX
    Explanations

    Code and technical documentation

    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
     Completion
    -0.29
     prox
    -0.29
    åŁºç¡Ģä¸Ĭ
    -0.28
    upe
    -0.26
     completes
    -0.26
     completion
    -0.26
     Claud
    -0.26
    诸èijĽ
    -0.25
    extract
    -0.25
     stacks
    -0.25
    POSITIVE LOGITS
    shaw
    0.30
    ä¸ĩä½Ļåħĥ
    0.25
    éļıä¹ĭ
    0.24
    onium
    0.23
    æľī大éĩıçļĦ
    0.23
     withStyles
    0.23
    ÙĤÙħ
    0.23
    .FontStyle
    0.23
    èµłéĢģ
    0.23
     cosine
    0.23
    Activations Density 14.588%

    No Known Activations