© 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. 30-TRANSCODER-HP
    7. 95230
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     пеÑĢе
    -0.28
    æŀķ头
    -0.26
    éĩijçīĮ
    -0.25
     sop
    -0.25
    ourcem
    -0.25
     vase
    -0.24
    ifes
    -0.24
    _skb
    -0.24
     Stan
    -0.24
    åī¯ä¸»å¸Ń
    -0.24
    POSITIVE LOGITS
    mas
    0.29
    .imp
    0.27
    大ä¼Ĺ
    0.27
    mall
    0.26
    pin
    0.26
    产ä¸ļåĮĸ
    0.26
    åģĩ
    0.25
     æĸ
    0.24
     %{
    0.24
    ?family
    0.24
    Activations Density 0.831%

    No Known Activations

    This feature has no known activations.