© 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. 64861
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ¼Ķç»İ
    -0.27
    夯å®ŀ
    -0.26
    究
    -0.26
    iens
    -0.26
    oger
    -0.25
    gies
    -0.25
    è¡£
    -0.25
     eigen
    -0.25
    weis
    -0.24
    å¤Ł
    -0.24
    POSITIVE LOGITS
    å©´
    0.27
    è§Ħ模æľĢ大
    0.26
    ayah
    0.25
    é®®
    0.25
    ç¬Ķ
    0.25
    -largest
    0.25
    åįĬå²Ľ
    0.25
    æľĢå°ı
    0.24
    åĩºèĩª
    0.24
    utherford
    0.24
    Activations Density 17.199%

    No Known Activations

    This feature has no known activations.