© 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. 86762
    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
     dec
    -0.28
    airs
    -0.27
    èĥº
    -0.25
     maker
    -0.25
    aires
    -0.25
    umes
    -0.24
     por
    -0.24
    ares
    -0.24
    bian
    -0.24
    èĢĮåİ»
    -0.24
    POSITIVE LOGITS
    utters
    0.28
    ddit
    0.28
    ä¸įç»ı
    0.28
    åģļä¸įåĪ°
    0.28
    éĤĦæĺ¯
    0.26
    驸
    0.25
     onError
    0.25
     ogl
    0.25
     incons
    0.25
     onNext
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.