© 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. 30-TRANSCODER-HP
    7. 94892
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     flushing
    -0.26
     gusto
    -0.26
     Cabin
    -0.26
    åį«è§Ĩ
    -0.26
    earer
    -0.25
    itter
    -0.25
    ARIO
    -0.24
     flush
    -0.24
     Needle
    -0.24
     Pepper
    -0.24
    POSITIVE LOGITS
    odem
    0.34
    antaged
    0.28
    ablish
    0.27
    æīĵæĸŃ
    0.27
    å±Ĥ级
    0.25
    æ®ĸæ°ij
    0.23
    اط
    0.23
    ä¸ĬçıŃæĹı
    0.23
    温åĴĮ
    0.23
    krit
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.