© 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. 40705
    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
    ä»ĭ
    -0.23
    åĮĸ解
    -0.23
    StackSize
    -0.23
    alc
    -0.22
     and
    -0.22
    ect
    -0.22
    ↵
    -0.22
    ält
    -0.22
    é»Ħ
    -0.22
    åıijçĶŁäºĨ
    -0.22
    POSITIVE LOGITS
     sidel
    0.26
    çľĭä¸įæĩĤ
    0.25
    夥
    0.24
     dreamed
    0.23
     scrim
    0.23
     denounced
    0.23
    好è¯Ħ
    0.23
     customizable
    0.23
     Guerrero
    0.23
     launder
    0.23
    Activations Density 7.112%

    No Known Activations

    This feature has no known activations.