© 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. 38546
    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
     either
    -0.27
    æĶ¾
    -0.27
    -caption
    -0.26
    aurants
    -0.26
     sector
    -0.26
     cylinder
    -0.24
    awy
    -0.24
    æĿ
    -0.24
     flat
    -0.24
    æ¨Ĺ
    -0.24
    POSITIVE LOGITS
    zw
    0.30
    zung
    0.29
    éĿ¢åħ·
    0.29
    çļĦéĹ®é¢ĺ
    0.27
    .experimental
    0.27
     Sisters
    0.27
    lte
    0.26
    å°ıå§IJå§IJ
    0.25
    æ°¸æģĴ
    0.25
    umba
    0.24
    Activations Density 5.696%

    No Known Activations

    This feature has no known activations.