© 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. 64853
    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
    fern
    -0.27
    è§ģ
    -0.26
     示
    -0.26
    åĬ©
    -0.25
    VIS
    -0.24
    龸
    -0.24
    vis
    -0.24
    è¨ĺ
    -0.24
    inst
    -0.24
    _rec
    -0.24
    POSITIVE LOGITS
    被æįķ
    0.27
    uem
    0.26
    isman
    0.25
    åľ¨éĩĮéĿ¢
    0.25
    è¾ľ
    0.25
    uell
    0.25
    urai
    0.24
    ailer
    0.24
    è¿Ļæł·åģļ
    0.24
    ubbles
    0.23
    Activations Density 13.789%

    No Known Activations

    This feature has no known activations.