© 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. 38555
    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
    hap
    -0.27
    oret
    -0.26
    åľ¨åºĬä¸Ĭ
    -0.25
    tle
    -0.23
    å§Ķå®£ä¼łéĥ¨
    -0.23
    ary
    -0.23
     clin
    -0.23
    é»ī
    -0.23
    deny
    -0.23
    izen
    -0.23
    POSITIVE LOGITS
    对åħ¶
    0.31
    ä¿Ŀ
    0.27
    对ä»ĸ们
    0.27
    对èĩªå·±çļĦ
    0.27
    çĶŁæĢģ
    0.26
    ç»Ļ人
    0.25
    对æĪij们
    0.25
    æ´¾
    0.25
    对该
    0.25
    æıı
    0.25
    Activations Density 31.951%

    No Known Activations

    This feature has no known activations.