© 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. 38770
    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
    AttributeName
    -0.28
    梦
    -0.26
    æĿĥçĽĬ
    -0.26
    è¿ĩ渡
    -0.25
    åľ¨è¿ĩ渡
    -0.25
    ündig
    -0.25
    çļĦåľ°åĽ¾
    -0.25
    otle
    -0.24
    说ä¸įå®ļ
    -0.24
    é©·
    -0.24
    POSITIVE LOGITS
     punct
    0.25
    iable
    0.25
    交
    0.24
     kind
    0.24
    Math
    0.24
     generic
    0.23
     reflex
    0.23
    ref
    0.23
    æĬĦ
    0.23
    æŃ£ç¢º
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.