© 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. 86892
    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
    Sigma
    -0.29
    ulk
    -0.28
    ItemSelectedListener
    -0.27
     Sigma
    -0.26
    ivation
    -0.25
    /slick
    -0.25
    acf
    -0.25
    /dat
    -0.24
     Communist
    -0.24
    éĩİçĶŁ
    -0.24
    POSITIVE LOGITS
    Âł↵
    0.26
     vener
    0.25
     heaven
    0.25
     дело
    0.24
    æݨéĢģ
    0.23
     decidedly
    0.23
    egrator
    0.23
     vụ
    0.23
    ç»ıæµİæĬĢæľ¯
    0.23
     resto
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.