© 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. 17820
    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
    é£İåħī
    -0.27
    oded
    -0.26
    å°½æĥħ
    -0.24
    rances
    -0.24
     bay
    -0.23
    aspers
    -0.23
     Accessed
    -0.23
    opl
    -0.23
    æ¸Ķæ°ij
    -0.23
    ody
    -0.22
    POSITIVE LOGITS
    çĽĸ
    0.28
    èĵĭ
    0.27
    phase
    0.27
     tort
    0.24
    ISTR
    0.24
    ç¦ħ
    0.23
    饶
    0.23
     fı
    0.23
     Ef
    0.22
    æ£į
    0.22
    Activations Density 2.267%

    No Known Activations

    This feature has no known activations.