© 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. 141813
    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
    åģļä¸ĢäºĽ
    -0.29
    roll
    -0.28
     Tell
    -0.27
    iotic
    -0.27
    shall
    -0.27
    åĪ©
    -0.26
     telling
    -0.26
    Âł
    -0.25
    \Web
    -0.25
    _setup
    -0.25
    POSITIVE LOGITS
    æľĢ容æĺĵ
    0.27
    æŀģæĺĵ
    0.27
    ä¸įç¦ģ
    0.26
    æĥĬ人
    0.26
     chic
    0.26
     mailed
    0.26
    æľĢçĪ±
    0.25
    åķĨä¸ļåĮĸ
    0.25
    ityEngine
    0.25
     escort
    0.25
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.