© 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. 24-TRANSCODER-HP
    7. 149352
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    attention
    -0.29
    ä»ĸ表示
    -0.27
    leen
    -0.25
     leaps
    -0.25
    ocate
    -0.24
     attention
    -0.23
    Attention
    -0.23
    åľ¨è¿Ļç§į
    -0.23
     recurs
    -0.23
    midd
    -0.23
    POSITIVE LOGITS
    æľīæĦı
    0.25
    istr
    0.24
    æĺİæĺİ
    0.24
    èĪŁ
    0.23
    dzi
    0.23
    å®ŀæĸ½ç»ĨåĪĻ
    0.22
    楦
    0.22
    å¯Ĥ
    0.21
     Britain
    0.21
    ach
    0.21
    Activations Density 0.678%

    No Known Activations

    This feature has no known activations.