© 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. 107530
    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
     hypers
    -0.28
    ä¹³
    -0.27
     cartel
    -0.27
     recap
    -0.25
    å»ĵ
    -0.25
     practise
    -0.25
     cla
    -0.25
     tra
    -0.24
     pedal
    -0.24
     Republic
    -0.24
    POSITIVE LOGITS
    åŃIJå¼¹
    0.27
    ÑĢÑĥж
    0.26
    æľ¬ç½ij
    0.26
    æľ¬ç«Ļ
    0.26
    erta
    0.25
     uncomment
    0.25
     ë¬
    0.25
    overn
    0.25
    AndView
    0.24
    imoto
    0.24
    Activations Density 22.912%

    No Known Activations

    This feature has no known activations.