© 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. 129078
    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
    wards
    -0.33
    اÙĥ
    -0.26
    ward
    -0.26
    Æ°á»Łng
    -0.26
    awei
    -0.25
    arde
    -0.25
    CharArray
    -0.25
    -done
    -0.24
     buc
    -0.24
    èĻļ空
    -0.24
    POSITIVE LOGITS
     prag
    0.24
    çIJĨæĥ³çļĦ
    0.24
    åħ±åĴĮ
    0.24
     Rx
    0.24
     margin
    0.24
     tension
    0.24
     sweat
    0.24
     Rub
    0.24
     priorit
    0.23
    margin
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.