© 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. 35-TRANSCODER-HP
    7. 38577
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    syscall
    -0.29
    athom
    -0.27
     nostr
    -0.26
     бил
    -0.25
    dom
    -0.25
    æĮĤåı·
    -0.25
     Beirut
    -0.25
    .tf
    -0.24
     REGISTER
    -0.24
     <|
    -0.24
    POSITIVE LOGITS
    -tip
    0.26
    èĵĿ天
    0.25
    èĭ«
    0.24
    责任æĦŁ
    0.24
    æĢ»å·¥ä¼ļ
    0.24
    åĮħåĽ´
    0.24
    ixer
    0.24
    èį£èªī
    0.23
    è¡Ģèħ¥
    0.23
     surrounding
    0.23
    Activations Density 10.018%

    No Known Activations

    This feature has no known activations.