© 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. 111102
    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
    ronics
    -0.30
    pip
    -0.24
    “But
    -0.24
    uler
    -0.23
    atk
    -0.23
    CATEGORY
    -0.23
    TOT
    -0.22
     sphere
    -0.22
    -sdk
    -0.22
    ucas
    -0.22
    POSITIVE LOGITS
     )(
    0.27
    çıįæĥľ
    0.26
    åij½é¢ĺ
    0.26
    Ïİ
    0.26
    ORN
    0.25
    wind
    0.25
    ç©¿éĢı
    0.24
    å¹³å®ī
    0.24
    åĽŀ头
    0.24
    åij½
    0.24
    Activations Density 0.024%

    No Known Activations

    This feature has no known activations.