© 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. 87129
    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
    Not in Any Lists

    No Comments

    Negative Logits
    utures
    -0.25
    oku
    -0.24
    odia
    -0.24
    ASTER
    -0.23
    tod
    -0.23
    ä¸Ģ款
    -0.23
    ospel
    -0.23
    actor
    -0.23
    wdx
    -0.23
    麦
    -0.23
    POSITIVE LOGITS
    èµĦæºIJä¼ĺåĬ¿
    0.28
    æĭĶ
    0.28
     Cub
    0.26
     cosmetic
    0.26
     observing
    0.26
     enquanto
    0.25
     juices
    0.25
    İ·
    0.25
    .addObserver
    0.25
    带走
    0.24
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.