© 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. 20-TRANSCODER-HP
    7. 62619
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çŃĴ
    -0.28
    compound
    -0.28
    aint
    -0.25
    çĹĩ
    -0.25
    icking
    -0.25
    ç±³ç²ī
    -0.25
    pcf
    -0.24
    åº
    -0.24
    ä¹ĥèĩ³
    -0.24
     HIT
    -0.24
    POSITIVE LOGITS
     grid
    0.26
    .hasMore
    0.24
     OTHERWISE
    0.24
    ãģĤãĤĬãģĮ
    0.24
     Robbins
    0.24
     kidding
    0.24
    енÑĮ
    0.23
    lei
    0.23
    chio
    0.23
    æĤ²è§Ĥ
    0.23
    Activations Density 9.166%

    No Known Activations

    This feature has no known activations.