© 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. 142730
    Prev
    Next
    INDEX
    Explanations

    Digits

    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
    лÑİ
    -0.28
    amat
    -0.27
    å®ĺ
    -0.27
    [list
    -0.26
    åı¯è§Ĩ
    -0.26
     padd
    -0.26
    è·Ŀ
    -0.26
     list
    -0.26
     exclus
    -0.25
    管
    -0.25
    POSITIVE LOGITS
    ÐĵлавнаÑı
    0.31
    cms
    0.26
    DIRECTORY
    0.25
    请åıĬæŶ
    0.25
    emory
    0.25
    remen
    0.25
    .qt
    0.24
    ://'
    0.23
     ours
    0.23
     Emp
    0.23
    Activations Density 11.432%

    No Known Activations