© 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. 38584
    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
    color
    -0.28
    _sign
    -0.28
     significant
    -0.28
    åľ¨æѤ
    -0.27
    -color
    -0.27
    sign
    -0.27
     signific
    -0.26
    .sign
    -0.25
    å°ıåŃIJ
    -0.25
     color
    -0.24
    POSITIVE LOGITS
    à¸ķร
    0.28
     Oman
    0.25
    âĢ¦)↵↵
    0.25
    ,âĢ¦↵↵
    0.24
    ulti
    0.24
     newsp
    0.24
    CEE
    0.23
    SURE
    0.23
    CATEGORY
    0.23
    licit
    0.23
    Activations Density 2.660%

    No Known Activations

    This feature has no known activations.