© 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. 38646
    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
    ilateral
    -0.26
     turquoise
    -0.25
     upside
    -0.25
    edReader
    -0.25
     contour
    -0.25
     sal
    -0.25
    ette
    -0.24
    å·¡åĽŀ
    -0.24
     tour
    -0.24
     cup
    -0.24
    POSITIVE LOGITS
     dost
    0.33
    ä¾Ľ
    0.26
    åIJĮ
    0.25
    outcome
    0.25
    nota
    0.25
    åħ¨
    0.25
    åħ¥
    0.25
     mies
    0.25
     bied
    0.25
    æŀ³
    0.25
    Activations Density 1.365%

    No Known Activations

    This feature has no known activations.