© 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. 108688
    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
    numer
    -0.26
    urons
    -0.25
    ä¹Łæĺ¯ä¸Ģ个
    -0.25
    änn
    -0.25
     pedal
    -0.24
     minded
    -0.24
    èĴľ
    -0.24
    çĭ®
    -0.24
    *</
    -0.24
    ilden
    -0.23
    POSITIVE LOGITS
    oogle
    0.30
    atten
    0.28
    DW
    0.27
    adder
    0.27
     halves
    0.26
     half
    0.26
    rides
    0.25
    ä¸Ĭåİ»
    0.25
     Watkins
    0.25
    lyn
    0.25
    Activations Density 20.661%

    No Known Activations

    This feature has no known activations.