© 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. 113116
    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
    orph
    -0.23
    asty
    -0.22
    ç»Į
    -0.22
    æīĭ表
    -0.22
    rophy
    -0.21
    bek
    -0.21
    woke
    -0.21
    rush
    -0.20
    ient
    -0.20
    tributes
    -0.20
    POSITIVE LOGITS
    æİ¥è¿ĩ
    0.24
    æºı
    0.22
    _Exception
    0.22
     alike
    0.21
     EXCEPTION
    0.21
    羣çļĦå¾Ī
    0.20
    帮åĬ©ä¼ģä¸ļ
    0.20
    äºĭæķħåıijçĶŁ
    0.20
     napisaÅĤ
    0.20
    ¢åįķ
    0.19
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.