© 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. 99134
    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
    å¼Ģåĩº
    -0.27
    åĨįçİ°
    -0.27
    派人
    -0.25
    åĬłçĽĸ
    -0.25
    mdir
    -0.25
     tá»ijt
    -0.25
     closure
    -0.25
     documentos
    -0.24
     sme
    -0.24
    çķĻä½ı
    -0.24
    POSITIVE LOGITS
    èģĶ绾
    0.26
    Configs
    0.25
     Diss
    0.25
    ==='
    0.25
    çĻ
    0.23
    è¾½
    0.23
    UNE
    0.23
    ensions
    0.23
    LEC
    0.22
    .rev
    0.22
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.