© 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. 63019
    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
    elves
    -0.28
    serter
    -0.25
    ervlet
    -0.25
    .party
    -0.25
    quine
    -0.25
    cken
    -0.25
    _cm
    -0.25
    åĨĬ
    -0.24
     Gem
    -0.24
    _publisher
    -0.24
    POSITIVE LOGITS
    æ´¾
    0.31
    æĥľ
    0.29
    åıijæĮ¥
    0.28
     US
    0.26
    so
    0.26
    isi
    0.25
     USA
    0.25
    æľĢéĩįè¦ģçļĦ
    0.25
    asics
    0.25
    ç¾İåĽ½
    0.25
    Activations Density 0.212%

    No Known Activations

    This feature has no known activations.