© 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. 86826
    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
    å¾ħ
    -0.28
     scales
    -0.28
     causes
    -0.26
    çĶ¨äºº
    -0.25
    .globalData
    -0.24
     experiences
    -0.24
     Bo
    -0.24
     apprec
    -0.24
     scrape
    -0.24
     thankfully
    -0.24
    POSITIVE LOGITS
    ặt
    0.28
    å¼
    0.26
    éĢŁåº¦å¿«
    0.25
    redicate
    0.25
    æijĦå½±å¸Ī
    0.24
    xCD
    0.24
    .cam
    0.24
     Filme
    0.24
    iterals
    0.24
    å®ĺæĸ¹ç½ijç«Ļ
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.