© 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. 140702
    Prev
    Next
    INDEX
    Explanations

    technical/academic topics

    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
    lard
    -0.28
    ofi
    -0.27
    IEWS
    -0.27
    è¾°
    -0.25
    ningen
    -0.25
    ãĥĬãĥ³
    -0.24
     outnumber
    -0.24
    åĢ¾åIJij
    -0.24
     Wells
    -0.23
     PyErr
    -0.23
    POSITIVE LOGITS
    .Must
    0.27
    Criterion
    0.26
    onomy
    0.26
    åij¦
    0.25
    æĭ¬
    0.24
     ecological
    0.23
    -reference
    0.23
    PUT
    0.23
    èĭ¦éļ¾
    0.23
     rip
    0.23
    Activations Density 1.056%

    No Known Activations