© 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. 99135
    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
     contr
    -0.25
    ulg
    -0.24
    佯
    -0.23
    溢
    -0.23
    licant
    -0.23
    edException
    -0.22
    è¿Īè¿Ľ
    -0.22
    rawid
    -0.22
    CG
    -0.22
     Contr
    -0.22
    POSITIVE LOGITS
    åĪĨæīĭ
    0.26
    aste
    0.24
    uÃŃ
    0.23
    çĦ¦
    0.23
    FI
    0.22
    æľ¬èº«å°±æĺ¯
    0.22
    selectAll
    0.22
     FI
    0.22
    rage
    0.22
     onSelect
    0.21
    Activations Density 0.021%

    No Known Activations

    This feature has no known activations.