© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 86925
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĬķèŀįèµĦ
    -0.25
    esor
    -0.24
     precedent
    -0.24
    太é«ĺ
    -0.24
    æĺ¯åIJ¦
    -0.24
    InitialState
    -0.23
    åIJĪä½ľ
    -0.23
    身
    -0.23
    帮
    -0.23
    ÃĤ
    -0.22
    POSITIVE LOGITS
    aturated
    0.24
    yards
    0.24
     Hamburg
    0.24
    hes
    0.23
    aware
    0.23
    èĢĮåİ»
    0.23
    -history
    0.23
     sequelize
    0.23
     hern
    0.23
    	go
    0.22
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.