© 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. 38775
    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
    è¿Ļ段
    -0.25
    aptor
    -0.24
     qualifying
    -0.24
    ãĤ³ãĥ¼ãĤ¹
    -0.24
    anzi
    -0.23
     concentrating
    -0.23
    åıĹ访
    -0.22
     uncover
    -0.22
    "].(
    -0.22
    è´£ç¼ĸ
    -0.22
    POSITIVE LOGITS
    ç¹ģ
    0.26
    ocrin
    0.25
    otypes
    0.24
    åħīæĺİ
    0.24
    jq
    0.24
    iaux
    0.23
     Bundy
    0.23
     zro
    0.23
    otyping
    0.23
    座
    0.23
    Activations Density 15.371%

    No Known Activations

    This feature has no known activations.