© 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. 130989
    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
    éķľ
    -0.29
     Rolled
    -0.29
    æ»ļ
    -0.28
    æݨéĢģ
    -0.28
    级
    -0.27
    æĴº
    -0.27
    社
    -0.25
    èIJİ
    -0.25
    amina
    -0.25
    company
    -0.25
    POSITIVE LOGITS
    è¿Ń
    0.27
    éĺī
    0.27
    azar
    0.25
    piar
    0.25
    æĬĬæīĭ
    0.24
    ç»ĪçĶŁ
    0.24
    abet
    0.24
    å¤ļéĩį
    0.23
    æĢª
    0.23
     Uint
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.