© 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. 142405
    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
    Not in Any Lists

    No Comments

    Negative Logits
     gums
    -0.26
    iq
    -0.26
    InputChange
    -0.25
     |_|
    -0.25
    gon
    -0.25
    毫æĹłçĸij
    -0.25
     blindly
    -0.24
    ews
    -0.24
    iline
    -0.24
    idx
    -0.24
    POSITIVE LOGITS
     Calder
    0.29
     trá»Ŀi
    0.29
    主导
    0.27
    è¿ĺèĥ½
    0.26
    ://{
    0.26
    举ä¾ĭ
    0.26
    éĨĴäºĨ
    0.25
    Ĥ¬
    0.25
    (admin
    0.24
    oundary
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.