© 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. 86900
    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
    isphere
    -0.27
    poke
    -0.26
     rocker
    -0.26
    鸣类
    -0.26
    æŃĮæĽ²
    -0.25
    å½»
    -0.24
    ä¿Ŀ驾
    -0.24
    abant
    -0.24
    è°ĥæķ´
    -0.24
    uliar
    -0.23
    POSITIVE LOGITS
     (::
    0.29
    åĵģçīĮçļĦ
    0.27
     arguments
    0.25
    ency
    0.25
    egree
    0.24
     BAR
    0.24
    %">
    0.24
    á»įng
    0.24
     federation
    0.23
    =args
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.