© 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. 38706
    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
    çݺ
    -0.28
    lsx
    -0.27
    uib
    -0.24
    æİ©
    -0.24
    礼
    -0.24
    è¿Ľå±ķ
    -0.24
     Cheer
    -0.24
     strapped
    -0.23
    è´«è¡Ģ
    -0.23
    ripe
    -0.23
    POSITIVE LOGITS
    eco
    0.28
    -driven
    0.27
    Navigator
    0.27
    arch
    0.26
     mortgage
    0.25
    serv
    0.25
    ä»ĸ们ä¼ļ
    0.24
     поли
    0.24
     aspir
    0.24
    -based
    0.24
    Activations Density 39.725%

    No Known Activations

    This feature has no known activations.