© 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. 27-TRANSCODER-HP
    7. 9632
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     homework
    -0.67
    çŃĶé¢ĺ
    -0.59
    ä½ľä¸ļ
    -0.58
     Homework
    -0.58
    è¯ķåį·
    -0.54
    çŃĶåį·
    -0.52
    è¯ķé¢ĺ
    -0.52
     exam
    -0.50
    çŁ¥è¯ĨçĤ¹
    -0.50
     answers
    -0.49
    POSITIVE LOGITS
    éĻ¢
    0.28
    롱
    0.27
    ellar
    0.24
     chick
    0.24
    <?
    0.24
    åĬĵ
    0.24
    reshold
    0.24
    çĶ¨åľ°
    0.24
    åħļä¸Ń央
    0.23
     //~
    0.23
    Activations Density 0.000%

    No Known Activations