© 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. 20-TRANSCODER-HP
    7. 140626
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¤ļå±Ĥ次
    -0.26
    楹
    -0.25
    磾
    -0.24
     set
    -0.24
    ãģĭãģ¤
    -0.24
     sets
    -0.24
    ÑĩнаÑı
    -0.24
    åģļé¥Ń
    -0.23
    åĬ³åĬ¨
    -0.23
    lem
    -0.23
    POSITIVE LOGITS
    @email
    0.28
    ç¦ģ
    0.27
    ánÃŃ
    0.26
    /grpc
    0.26
    бан
    0.26
     Sabb
    0.25
    reck
    0.25
    groupName
    0.25
    igel
    0.24
     freezer
    0.24
    Activations Density 17.145%

    No Known Activations

    This feature has no known activations.