© 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. 128890
    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
    æĮĩ
    -0.28
    éªĸ
    -0.27
    NotFoundError
    -0.26
    æŃĩ
    -0.26
    .ms
    -0.25
    eted
    -0.25
    ÑĤика
    -0.25
     close
    -0.24
    acen
    -0.24
    éļĨ
    -0.24
    POSITIVE LOGITS
    ç¾İæĸ¹
    0.25
    -HT
    0.25
    åºĹåĨħ
    0.24
     Grinding
    0.24
     yên
    0.23
    -License
    0.23
    esModule
    0.23
    ä¸¥æł¼æĮīçħ§
    0.23
    èĬį
    0.23
    interest
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.