© 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. 40772
    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
     darn
    -0.26
     hairs
    -0.25
    å¹´ä¹ĭä¹ħ
    -0.25
    olics
    -0.25
    auer
    -0.24
    .calls
    -0.24
     walmart
    -0.24
    plt
    -0.24
    unity
    -0.23
     Mets
    -0.23
    POSITIVE LOGITS
    ä¸Ģæľ¬
    0.28
    åįij
    0.26
    slave
    0.25
    åĴĮæľįåĬ¡
    0.24
    "],"
    0.24
    ç³ľ
    0.24
    ä¸Ģæľ¬ä¹¦
    0.24
    HI
    0.24
    -highlight
    0.23
    Lite
    0.23
    Activations Density 26.582%

    No Known Activations

    This feature has no known activations.