© 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. 20-TRANSCODER-HP
    7. 62581
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¤Ĥ
    -0.26
    äºĨèĩªå·±çļĦ
    -0.24
    upiter
    -0.23
    çĩ§
    -0.23
     matcher
    -0.23
    _unicode
    -0.23
    PageIndex
    -0.23
    èį¼
    -0.23
    ç¿Ĵ
    -0.23
    odzi
    -0.22
    POSITIVE LOGITS
    (func
    0.26
    åħ±åĴĮ
    0.26
    éĨĴ
    0.25
     gamm
    0.25
    éĩįçĤ¹é¢ĨåŁŁ
    0.24
    æ¸ħæ°´
    0.24
    å¼±çĤ¹
    0.24
    æ³
    0.24
     unb
    0.24
    åĽŀ头
    0.24
    Activations Density 33.512%

    No Known Activations

    This feature has no known activations.