© 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. 40638
    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
    adic
    -0.27
    aven
    -0.25
    ponge
    -0.25
    mlin
    -0.25
    á»ģ
    -0.25
    交
    -0.24
    ppo
    -0.24
    levard
    -0.24
    çīĪ
    -0.24
    á»Ģ
    -0.24
    POSITIVE LOGITS
     Sacr
    0.30
    èµŀèµı
    0.27
    èĥ½çľĭåĩº
    0.25
     Sequence
    0.25
    -Za
    0.24
     Volt
    0.24
    ä¹Łä¸įèĥ½
    0.24
     Recognition
    0.24
     Point
    0.23
     hä
    0.23
    Activations Density 23.772%

    No Known Activations

    This feature has no known activations.