© 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. 62749
    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
    enso
    -0.28
    sig
    -0.27
    inent
    -0.27
    è§ģ
    -0.27
    åİĮ
    -0.25
    تاØŃ
    -0.24
    vox
    -0.24
     Valley
    -0.24
    ynes
    -0.24
    åĽłä¸ºå®ĥ
    -0.23
    POSITIVE LOGITS
    /platform
    0.26
    æĤ²
    0.25
    ibase
    0.25
     inherited
    0.25
    änge
    0.24
    ä¼ļè®©ä½ł
    0.24
    GRES
    0.24
    åĴĮæĬĢæľ¯
    0.23
     faults
    0.23
    SSL
    0.23
    Activations Density 7.931%

    No Known Activations

    This feature has no known activations.