© 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. 40698
    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
    ä¸įåħĭä¸įåıĬ
    -0.26
     Mile
    -0.25
    âĹĦ
    -0.24
    bö
    -0.23
    æĭ¶
    -0.23
    keiten
    -0.23
    edException
    -0.23
    ailles
    -0.23
    ön
    -0.23
    å°ı康社ä¼ļ
    -0.23
    POSITIVE LOGITS
     earm
    0.28
    æĹłå½¢
    0.26
    ä¼ı
    0.24
     better
    0.24
    éĿ¢ä¸Ĭ
    0.24
    clo
    0.24
    è¿Ļ两ç§į
    0.23
    oon
    0.23
    code
    0.23
    è¶Ĭ
    0.23
    Activations Density 13.630%

    No Known Activations

    This feature has no known activations.