© 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. 111069
    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
    wal
    -0.29
    ä¸Ģ个æĺ¯
    -0.27
    rown
    -0.27
    ima
    -0.26
    çĶŁ
    -0.25
     Imper
    -0.24
     Chamber
    -0.24
    HCI
    -0.24
    ɵ
    -0.24
    issen
    -0.23
    POSITIVE LOGITS
    为æѤ
    0.24
    è¿ijè§Ĩ
    0.23
     Bronx
    0.23
     subsequent
    0.23
    å°±æѤ
    0.23
    çĬ´
    0.23
    =search
    0.22
     recently
    0.22
    èĩ¼
    0.22
     Farms
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.