© 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. 35-TRANSCODER-HP
    7. 40790
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     reconciliation
    -0.26
     resent
    -0.26
     mata
    -0.24
     prest
    -0.23
     kla
    -0.23
     preamble
    -0.23
    =res
    -0.23
     complaints
    -0.22
     reconc
    -0.22
     thumbs
    -0.22
    POSITIVE LOGITS
    ovan
    0.29
    works
    0.29
    agu
    0.28
    ague
    0.27
    erox
    0.27
    etric
    0.26
    arias
    0.26
     Bearings
    0.26
    él
    0.25
    iras
    0.25
    Activations Density 5.739%

    No Known Activations

    This feature has no known activations.