© 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. 63504
    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
    æ²±
    -0.26
    è¹Ń
    -0.26
    ÑĦи
    -0.25
    ppe
    -0.24
    缦
    -0.24
    åĮĹ京大åѦ
    -0.24
    å¢ŀ
    -0.24
     bottom
    -0.24
     ÑĢеж
    -0.24
    orst
    -0.24
    POSITIVE LOGITS
    azen
    0.24
    大æĪĺ
    0.24
    ãĤıãĤĬ
    0.24
    åĬłçıŃ
    0.24
    ä¸Ĭä¼ł
    0.24
     dedicate
    0.24
    -upload
    0.24
     Variety
    0.23
    pta
    0.23
    Suit
    0.23
    Activations Density 0.257%

    No Known Activations

    This feature has no known activations.