© 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. 31-TRANSCODER-HP
    7. 17760
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    弥补
    -0.28
    ustin
    -0.26
    emet
    -0.25
    igid
    -0.24
     Morr
    -0.24
    redit
    -0.24
    deck
    -0.24
    itaire
    -0.23
    ustr
    -0.23
    æ¤į
    -0.23
    POSITIVE LOGITS
     scal
    0.28
    íĥĪ
    0.27
    ä¸Ģé¦ĸ
    0.26
    ارÙĬ
    0.26
    çŁ¾
    0.26
     fluid
    0.25
    ax
    0.25
     crypt
    0.25
    asser
    0.25
     lateral
    0.24
    Activations Density 0.028%

    No Known Activations