© 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. 63734
    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
     vir
    -0.26
     subsequent
    -0.26
     sense
    -0.25
    icular
    -0.25
     detal
    -0.25
    itated
    -0.25
    .io
    -0.25
    رÙĪÙĨ
    -0.25
     amb
    -0.24
    ly
    -0.24
    POSITIVE LOGITS
    Messaging
    0.28
    zag
    0.27
    pong
    0.26
    åħ±
    0.26
     Ebony
    0.26
    æĬ¨
    0.26
    çģ¶
    0.25
    ä¸ĵä¸ļæĬĢæľ¯
    0.25
    jets
    0.25
     {};č↵
    0.23
    Activations Density 16.170%

    No Known Activations

    This feature has no known activations.