© 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. 40569
    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¸Ŀä¸Ŀ
    -0.31
    ycl
    -0.27
    çĤī
    -0.26
    稳åģ¥
    -0.25
     weigh
    -0.25
    éĢ¢
    -0.24
     ton
    -0.24
     tonnes
    -0.24
    hlen
    -0.24
     Äijáng
    -0.24
    POSITIVE LOGITS
    åĵģç±»
    0.25
    ä¸įå°ij
    0.25
    ergy
    0.25
    atar
    0.25
    æ³Ĭ
    0.25
    éis
    0.25
    ervo
    0.24
    æĺİçĻ½
    0.24
    à¸ķà¸Ńà¸ļ
    0.24
    aware
    0.24
    Activations Density 31.977%

    No Known Activations

    This feature has no known activations.