© 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. 99270
    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
    åįļçī©
    -0.28
     nâ
    -0.23
    compact
    -0.23
     resorts
    -0.23
    AAD
    -0.23
    X
    -0.23
    ems
    -0.23
    è¯ķè¡Į
    -0.23
    ãģĤãĤĮ
    -0.23
    ppers
    -0.22
    POSITIVE LOGITS
     sclerosis
    0.26
    çļĦ产åĵģ
    0.25
    äºĨä»ĸçļĦ
    0.24
    çļĦåħ³æ³¨
    0.24
    ç»ĿæľĽ
    0.23
    ä¸įç¡®å®ļ
    0.22
    å¹ħ度
    0.22
    [](
    0.22
    afia
    0.22
    产åĵģçļĦ
    0.22
    Activations Density 0.020%

    No Known Activations

    This feature has no known activations.