© 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. 38550
    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
    交éĢļ
    -0.32
    æľĿ
    -0.32
    æĽ´ä¸º
    -0.29
    æķ£
    -0.28
    æİ©
    -0.27
    æĥħ
    -0.27
    æºľ
    -0.26
    ãģĵãģ¨
    -0.26
    mean
    -0.26
    èĢĮä¸Ķ
    -0.26
    POSITIVE LOGITS
     cre
    0.27
    oret
    0.27
    æĥ
    0.26
     rare
    0.26
     bre
    0.26
     solved
    0.25
     com
    0.25
     Abyss
    0.25
    MLS
    0.25
     clin
    0.24
    Activations Density 0.418%

    No Known Activations

    This feature has no known activations.