© 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. 112969
    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
    çłĶ
    -0.23
    æīĩ
    -0.23
     suce
    -0.22
     Sect
    -0.22
    topl
    -0.22
    æľºä¼ļ
    -0.22
    strap
    -0.22
    èµ·çĤ¹
    -0.22
     %.
    -0.22
     Highest
    -0.21
    POSITIVE LOGITS
    èı°
    0.23
    yms
    0.22
    iban
    0.22
    ↵↵↵
    0.22
    uma
    0.22
    andal
    0.22
    ↵        ↵
    0.22
    AndServe
    0.22
    $$$$
    0.21
    stä
    0.20
    Activations Density 0.033%

    No Known Activations

    This feature has no known activations.