© 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. 52602
    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
     correspond
    -0.28
     aggregate
    -0.27
     progression
    -0.26
     aggreg
    -0.25
     Sup
    -0.25
     dela
    -0.25
    线
    -0.25
     Ele
    -0.25
     Ag
    -0.23
     w
    -0.23
    POSITIVE LOGITS
    髦
    0.28
    ENN
    0.27
    eltas
    0.26
    SES
    0.26
    IEL
    0.25
    icol
    0.25
    SED
    0.24
     bm
    0.24
    Ñģли
    0.24
     Idol
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.