© 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. 141765
    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
    åľ¨è¿ĩåİ»
    -0.27
    encies
    -0.26
    {return
    -0.25
    ivation
    -0.25
    	exec
    -0.24
    åľ¨å®¶
    -0.24
    jamin
    -0.24
    麻
    -0.24
    truncate
    -0.24
    代åĬŀ
    -0.24
    POSITIVE LOGITS
    æł·åŃIJ
    0.27
    ANI
    0.27
     Tour
    0.26
    å»ĵ
    0.26
    ani
    0.26
     Presidents
    0.24
    eh
    0.24
    æľĢå°ij
    0.24
     Course
    0.24
    å»Ĭ
    0.23
    Activations Density 23.744%

    No Known Activations

    This feature has no known activations.