© 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. 97162
    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
    Negative Logits
    IGH
    -0.28
    je
    -0.28
     Adams
    -0.25
    æľ¬ä¹¦
    -0.24
    ķìĿ¸
    -0.24
    &m
    -0.24
    oltage
    -0.24
    jeta
    -0.24
    elt
    -0.24
    EventType
    -0.23
    POSITIVE LOGITS
    ago
    0.31
    楼
    0.27
    社ä¼ļåĮĸ
    0.27
    orient
    0.27
    æĦıæĦ¿
    0.27
    éĶĭ
    0.26
     Orc
    0.26
    cellent
    0.26
    ConfigurationException
    0.26
    æݨèįIJéĺħ读
    0.25
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.