© 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. 129180
    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
    广
    -0.28
     trần
    -0.28
    à¸Ńาà¸ģาศ
    -0.26
    itals
    -0.26
    ä»ĺãģij
    -0.26
    oreal
    -0.25
     '::
    -0.25
    reck
    -0.24
    åĨħéĻĨ
    -0.24
     Caj
    -0.24
    POSITIVE LOGITS
    ascar
    0.27
    /mp
    0.26
    /fr
    0.26
    fr
    0.26
    飩
    0.25
    涣
    0.24
     fr
    0.24
    éģ¿
    0.24
    asc
    0.24
     ridic
    0.24
    Activations Density 33.448%

    No Known Activations

    This feature has no known activations.