© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142021
    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
    åĪ©çĶ¨æĤ¨çļĦ
    -0.27
    .decorate
    -0.26
    ibly
    -0.26
    uct
    -0.26
    ç¡®
    -0.25
     Advantage
    -0.24
     ofType
    -0.24
    other
    -0.24
    ouve
    -0.24
     duct
    -0.23
    POSITIVE LOGITS
    &T
    0.28
     bum
    0.24
    iena
    0.23
     {:.
    0.22
     tent
    0.22
     YE
    0.22
     TODAY
    0.22
    YNAM
    0.22
     ph
    0.22
    folk
    0.22
    Activations Density 0.957%

    No Known Activations

    This feature has no known activations.