© 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. 38582
    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
    idy
    -0.30
     nowhere
    -0.30
    å¿Ĺ
    -0.26
    oss
    -0.26
    rol
    -0.25
     organisation
    -0.25
    ordering
    -0.24
     ATTRIBUTE
    -0.24
    RT
    -0.24
    ali
    -0.24
    POSITIVE LOGITS
     tick
    0.28
    ä¹ĭæĥħ
    0.27
     Past
    0.26
    TickCount
    0.26
    ác
    0.25
    éħIJ
    0.24
    ennes
    0.24
     iVar
    0.24
     skulls
    0.23
    ä¸Ģåı°
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.