© 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. 33-TRANSCODER-HP
    7. 54676
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    âĪĿ
    -0.28
    bro
    -0.27
    åįģåŃĹ
    -0.27
    IFT
    -0.26
     airs
    -0.26
    æĬ¥è®°èĢħ
    -0.26
    è¿©
    -0.25
    apore
    -0.24
    apia
    -0.24
    бой
    -0.24
    POSITIVE LOGITS
    缩
    0.28
    åĭĴ
    0.28
     Poly
    0.27
    hot
    0.26
    ngoing
    0.26
    iÅŁ
    0.26
    acemark
    0.26
     Transit
    0.25
     unic
    0.25
    icc
    0.24
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.